http://gisaxs.com/index.php?action=history&feed=atom&title=AI_safety 2026-04-08T18:08:24Z Revision history for this page on the wiki MediaWiki 1.31.7 http://gisaxs.com/index.php?title=AI_safety&diff=8764&oldid=prev 2026-03-30T16:37:15Z

<p>‎<span dir="auto"><span class="autocomment">Status</span></span></p> <table class="diff diff-contentalign-left" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 16:37, 30 March 2026</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l55" >Line 55:</td> <td colspan="2" class="diff-lineno">Line 55:</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2025-01: [https://assets.publishing.service.gov.uk/media/679a0c48a77d250007d313ee/International_AI_Safety_Report_2025_accessible_f.pdf International Safety Report: The International Scientific Report on the Safety of Advanced AI (January 2025)]</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2025-01: [https://assets.publishing.service.gov.uk/media/679a0c48a77d250007d313ee/International_AI_Safety_Report_2025_accessible_f.pdf International Safety Report: The International Scientific Report on the Safety of Advanced AI (January 2025)]</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* [https://ailabwatch.org/ AI Lab Watch] (safety scorecard)</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* [https://ailabwatch.org/ AI Lab Watch] (safety scorecard)</div></td></tr> <tr><td colspan="2">&#160;</td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">* 2026-03: [https://windowsontheory.org/2026/03/30/the-state-of-ai-safety-in-four-fake-graphs/ The state of AI safety in four fake graphs]</ins></div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Assessmment==</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Assessmment==</div></td></tr> </table>

KevinYager http://gisaxs.com/index.php?title=AI_safety&diff=8741&oldid=prev 2026-03-19T17:55:58Z

<p>‎<span dir="auto"><span class="autocomment">Description of Safety Concerns</span></span></p> <table class="diff diff-contentalign-left" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 17:55, 19 March 2026</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l27" >Line 27:</td> <td colspan="2" class="diff-lineno">Line 27:</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* [https://www.lesswrong.com/posts/N6vZEnCn6A95Xn39p/are-we-in-an-ai-overhang Overhang]</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* [https://www.lesswrong.com/posts/N6vZEnCn6A95Xn39p/are-we-in-an-ai-overhang Overhang]</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* [https://www.alignmentforum.org/posts/pdaGN6pQyQarFHXF4/reward-is-not-the-optimization-target Reward is not the optimization target] (Alex Turner)</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* [https://www.alignmentforum.org/posts/pdaGN6pQyQarFHXF4/reward-is-not-the-optimization-target Reward is not the optimization target] (Alex Turner)</div></td></tr> <tr><td colspan="2">&#160;</td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">* 80,000 hours:</ins></div></td></tr> <tr><td colspan="2">&#160;</td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">** [https://80000hours.org/problem-profiles/risks-from-power-seeking-ai/ Risks from power-seeking AI systems]</ins></div></td></tr> <tr><td colspan="2">&#160;</td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">** [https://80000hours.org/problem-profiles/gradual-disempowerment/ Gradual disempowerment]</ins></div></td></tr> <tr><td colspan="2">&#160;</td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">** [https://80000hours.org/problem-profiles/catastrophic-ai-misuse/ Catastrophic AI misuse]</ins></div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Medium-term Risks==</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Medium-term Risks==</div></td></tr> </table>

KevinYager http://gisaxs.com/index.php?title=AI_safety&diff=8739&oldid=prev 2026-03-18T17:37:10Z

<p>‎<span dir="auto"><span class="autocomment">Research</span></span></p> <table class="diff diff-contentalign-left" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 17:37, 18 March 2026</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l118" >Line 118:</td> <td colspan="2" class="diff-lineno">Line 118:</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2026-02: [https://arxiv.org/pdf/2601.23045 The Hot Mess of AI: How Does Misalignment Scale with Model Intelligence and Task Complexity?] (Anthropic [https://alignment.anthropic.com/2026/hot-mess-of-ai/ blog])</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2026-02: [https://arxiv.org/pdf/2601.23045 The Hot Mess of AI: How Does Misalignment Scale with Model Intelligence and Task Complexity?] (Anthropic [https://alignment.anthropic.com/2026/hot-mess-of-ai/ blog])</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2026-03: [https://cdn.openai.com/pdf/a21c39c1-fa07-41db-9078-973a12620117/cot_controllability.pdf Reasoning Models Struggle to Control their Chains of Thought] (OpenAI [https://openai.com/index/reasoning-models-chain-of-thought-controllability/ blog])</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2026-03: [https://cdn.openai.com/pdf/a21c39c1-fa07-41db-9078-973a12620117/cot_controllability.pdf Reasoning Models Struggle to Control their Chains of Thought] (OpenAI [https://openai.com/index/reasoning-models-chain-of-thought-controllability/ blog])</div></td></tr> <tr><td colspan="2">&#160;</td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">* 2026-03: [https://truthful.ai/consciousness_cluster.pdf The Consciousness Cluster: Preferences of Models that Claim to be Conscious]</ins></div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Demonstrations of Negative Use Capabilities==</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Demonstrations of Negative Use Capabilities==</div></td></tr> </table>

KevinYager http://gisaxs.com/index.php?title=AI_safety&diff=8726&oldid=prev 2026-03-12T16:42:39Z

<p>‎<span dir="auto"><span class="autocomment">Light</span></span></p> <table class="diff diff-contentalign-left" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 16:42, 12 March 2026</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l1" >Line 1:</td> <td colspan="2" class="diff-lineno">Line 1:</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>=Learning Resources=</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>=Learning Resources=</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Light==</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Light==</div></td></tr> <tr><td class='diff-marker'>−</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><del style="font-weight: bold; text-decoration: none;">* [https://www.youtube.com/watch?v=xfMQ7hzyFW4 Writing Doom] (27m video): short film on Superintelligence (2024)</del></div></td><td colspan="2">&#160;</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* [https://orxl.org/ai-doom.html a casual intro to AI doom and alignment] (2022)</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* [https://orxl.org/ai-doom.html a casual intro to AI doom and alignment] (2022)</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* Anthony Aguirre: [https://keepthefuturehuman.ai/ Keep The Future Human]</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* Anthony Aguirre: [https://keepthefuturehuman.ai/ Keep The Future Human]</div></td></tr> <tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l11" >Line 11:</td> <td colspan="2" class="diff-lineno">Line 10:</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>** Text version: Center for Humane Technology: [https://centerforhumanetechnology.substack.com/p/the-narrow-path-why-ai-is-our-ultimate The Narrow Path: Why AI is Our Ultimate Test and Greatest Invitation]</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>** Text version: Center for Humane Technology: [https://centerforhumanetechnology.substack.com/p/the-narrow-path-why-ai-is-our-ultimate The Narrow Path: Why AI is Our Ultimate Test and Greatest Invitation]</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* [https://x.com/KeiranJHarris/status/1935429439476887594 Fable about Transformative AI]</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* [https://x.com/KeiranJHarris/status/1935429439476887594 Fable about Transformative AI]</div></td></tr> <tr><td colspan="2">&#160;</td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">* 2024-10: [https://www.youtube.com/watch?v=xfMQ7hzyFW4 Writing Doom]: short film on Superintelligence (27m video)</ins></div></td></tr> <tr><td colspan="2">&#160;</td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">* 2026-03: [https://www.youtube.com/watch?v=Nl7-bRFSZBs The AI book that&#039;s freaking out national security advisors] (44m video)</ins></div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Deep==</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Deep==</div></td></tr> </table>

KevinYager http://gisaxs.com/index.php?title=AI_safety&diff=8710&oldid=prev 2026-03-05T20:31:57Z

<p>‎<span dir="auto"><span class="autocomment">Research</span></span></p> <table class="diff diff-contentalign-left" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 20:31, 5 March 2026</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l116" >Line 116:</td> <td colspan="2" class="diff-lineno">Line 116:</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>** 2025-02: Preprint: [https://martins1612.github.io/emergent_misalignment_betley.pdf Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs]</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>** 2025-02: Preprint: [https://martins1612.github.io/emergent_misalignment_betley.pdf Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs]</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2026-02: [https://arxiv.org/pdf/2601.23045 The Hot Mess of AI: How Does Misalignment Scale with Model Intelligence and Task Complexity?] (Anthropic [https://alignment.anthropic.com/2026/hot-mess-of-ai/ blog])</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2026-02: [https://arxiv.org/pdf/2601.23045 The Hot Mess of AI: How Does Misalignment Scale with Model Intelligence and Task Complexity?] (Anthropic [https://alignment.anthropic.com/2026/hot-mess-of-ai/ blog])</div></td></tr> <tr><td colspan="2">&#160;</td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">* 2026-03: [https://cdn.openai.com/pdf/a21c39c1-fa07-41db-9078-973a12620117/cot_controllability.pdf Reasoning Models Struggle to Control their Chains of Thought] (OpenAI [https://openai.com/index/reasoning-models-chain-of-thought-controllability/ blog])</ins></div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Demonstrations of Negative Use Capabilities==</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Demonstrations of Negative Use Capabilities==</div></td></tr> </table>

KevinYager http://gisaxs.com/index.php?title=AI_safety&diff=8665&oldid=prev 2026-02-16T16:13:17Z

<p>‎<span dir="auto"><span class="autocomment">Medium-term Risks</span></span></p> <table class="diff diff-contentalign-left" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 16:13, 16 February 2026</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l37" >Line 37:</td> <td colspan="2" class="diff-lineno">Line 37:</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2026-01: [https://www.science.org/doi/10.1126/science.adz1697 How malicious AI swarms can threaten democracy: The fusion of agentic AI and LLMs marks a new frontier in information warfare] (Science Magazine, [https://arxiv.org/abs/2506.06299 preprint])</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2026-01: [https://www.science.org/doi/10.1126/science.adz1697 How malicious AI swarms can threaten democracy: The fusion of agentic AI and LLMs marks a new frontier in information warfare] (Science Magazine, [https://arxiv.org/abs/2506.06299 preprint])</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2026-01: [https://www.darioamodei.com/essay/the-adolescence-of-technology The Adolescence of Technology: Confronting and Overcoming the Risks of Powerful AI] (Dario Amodei)</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2026-01: [https://www.darioamodei.com/essay/the-adolescence-of-technology The Adolescence of Technology: Confronting and Overcoming the Risks of Powerful AI] (Dario Amodei)</div></td></tr> <tr><td colspan="2">&#160;</td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">* 2026-02: [https://www.noahpinion.blog/p/updated-thoughts-on-ai-risk Updated thoughts on AI risk: Things have gotten scarier since 2023] ([https://x.com/Noahpinion Noah Smith])</ins></div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Long-term&#160; (x-risk)==</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Long-term&#160; (x-risk)==</div></td></tr> </table>

KevinYager http://gisaxs.com/index.php?title=AI_safety&diff=8613&oldid=prev 2026-02-03T17:57:28Z

<p>‎<span dir="auto"><span class="autocomment">Research</span></span></p> <table class="diff diff-contentalign-left" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 17:57, 3 February 2026</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l114" >Line 114:</td> <td colspan="2" class="diff-lineno">Line 114:</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2026-01: [https://www.nature.com/articles/s41586-025-09937-5 Training large language models on narrow tasks can lead to broad misalignment]</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2026-01: [https://www.nature.com/articles/s41586-025-09937-5 Training large language models on narrow tasks can lead to broad misalignment]</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>** 2025-02: Preprint: [https://martins1612.github.io/emergent_misalignment_betley.pdf Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs]</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>** 2025-02: Preprint: [https://martins1612.github.io/emergent_misalignment_betley.pdf Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs]</div></td></tr> <tr><td class='diff-marker'>−</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>* 2026-02: [https://<del class="diffchange diffchange-inline">alignment</del>.<del class="diffchange diffchange-inline">anthropic.com</del>/<del class="diffchange diffchange-inline">2026/hot-mess-of-ai</del>/ The Hot Mess of AI: How Does Misalignment Scale with Model Intelligence and Task Complexity?]</div></td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>* 2026-02: [https://<ins class="diffchange diffchange-inline">arxiv</ins>.<ins class="diffchange diffchange-inline">org</ins>/<ins class="diffchange diffchange-inline">pdf</ins>/<ins class="diffchange diffchange-inline">2601.23045 </ins>The Hot Mess of AI: How Does Misalignment Scale with Model Intelligence and Task Complexity?] <ins class="diffchange diffchange-inline">(Anthropic [https://alignment.anthropic.com/2026/hot-mess-of-ai/ blog])</ins></div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Demonstrations of Negative Use Capabilities==</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Demonstrations of Negative Use Capabilities==</div></td></tr> </table>

KevinYager http://gisaxs.com/index.php?title=AI_safety&diff=8612&oldid=prev 2026-02-03T17:55:19Z

<p>‎<span dir="auto"><span class="autocomment">Research</span></span></p> <table class="diff diff-contentalign-left" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 17:55, 3 February 2026</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l114" >Line 114:</td> <td colspan="2" class="diff-lineno">Line 114:</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2026-01: [https://www.nature.com/articles/s41586-025-09937-5 Training large language models on narrow tasks can lead to broad misalignment]</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2026-01: [https://www.nature.com/articles/s41586-025-09937-5 Training large language models on narrow tasks can lead to broad misalignment]</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>** 2025-02: Preprint: [https://martins1612.github.io/emergent_misalignment_betley.pdf Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs]</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>** 2025-02: Preprint: [https://martins1612.github.io/emergent_misalignment_betley.pdf Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs]</div></td></tr> <tr><td colspan="2">&#160;</td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">* 2026-02: [https://alignment.anthropic.com/2026/hot-mess-of-ai/ The Hot Mess of AI: How Does Misalignment Scale with Model Intelligence and Task Complexity?]</ins></div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Demonstrations of Negative Use Capabilities==</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Demonstrations of Negative Use Capabilities==</div></td></tr> </table>

KevinYager http://gisaxs.com/index.php?title=AI_safety&diff=8605&oldid=prev 2026-02-01T16:59:43Z

<p>‎<span dir="auto"><span class="autocomment">Medium-term Risks</span></span></p> <table class="diff diff-contentalign-left" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 16:59, 1 February 2026</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l28" >Line 28:</td> <td colspan="2" class="diff-lineno">Line 28:</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Medium-term Risks==</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Medium-term Risks==</div></td></tr> <tr><td class='diff-marker'>−</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>* 2023-04: [https://www.youtube.com/watch?v=xoVJKj8lcNQ A.I. Dilemma – Tristan Harris and Aza Raskin” (video)] ([https://assets-global .website-files.com/5f0e1294f002b1bb26e1f304/64224a9051a6637c1b60162a_65-your-undivided-attention-The-AI-Dilemma-transcript.pdf podcast transcript]): raises concern about human ability to handle these transformations</div></td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>* 2023-04: [https://www.youtube.com/watch?v=xoVJKj8lcNQ A.I. Dilemma – Tristan Harris and Aza Raskin” (video)] ([https://assets-global.website-files.com/5f0e1294f002b1bb26e1f304/64224a9051a6637c1b60162a_65-your-undivided-attention-The-AI-Dilemma-transcript.pdf podcast transcript]): raises concern about human ability to handle these transformations</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2023-04: [https://www.youtube.com/watch?v=KCSsKV5F4xc Daniel Schmachtenberger and Liv Boeree (video)]: AI could accelerate perverse social dynamics</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2023-04: [https://www.youtube.com/watch?v=KCSsKV5F4xc Daniel Schmachtenberger and Liv Boeree (video)]: AI could accelerate perverse social dynamics</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2023-10: [https://arxiv.org/pdf/2310.11986 Sociotechnical Safety Evaluation of Generative AI Systems] (Google DeepMind)</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2023-10: [https://arxiv.org/pdf/2310.11986 Sociotechnical Safety Evaluation of Generative AI Systems] (Google DeepMind)</div></td></tr> </table>

KevinYager http://gisaxs.com/index.php?title=AI_safety&diff=8604&oldid=prev 2026-02-01T16:59:21Z

<p>‎<span dir="auto"><span class="autocomment">Medium-term Risks</span></span></p> <table class="diff diff-contentalign-left" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #222; text-align: center;">Revision as of 16:59, 1 February 2026</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l36" >Line 36:</td> <td colspan="2" class="diff-lineno">Line 36:</td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2025-06: [https://arxiv.org/abs/2506.20702 The Singapore Consensus on Global AI Safety Research Priorities]</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2025-06: [https://arxiv.org/abs/2506.20702 The Singapore Consensus on Global AI Safety Research Priorities]</div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2026-01: [https://www.science.org/doi/10.1126/science.adz1697 How malicious AI swarms can threaten democracy: The fusion of agentic AI and LLMs marks a new frontier in information warfare] (Science Magazine, [https://arxiv.org/abs/2506.06299 preprint])</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>* 2026-01: [https://www.science.org/doi/10.1126/science.adz1697 How malicious AI swarms can threaten democracy: The fusion of agentic AI and LLMs marks a new frontier in information warfare] (Science Magazine, [https://arxiv.org/abs/2506.06299 preprint])</div></td></tr> <tr><td colspan="2">&#160;</td><td class='diff-marker'>+</td><td style="color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">* 2026-01: [https://www.darioamodei.com/essay/the-adolescence-of-technology The Adolescence of Technology: Confronting and Overcoming the Risks of Powerful AI] (Dario Amodei)</ins></div></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr> <tr><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Long-term&#160; (x-risk)==</div></td><td class='diff-marker'>&#160;</td><td style="background-color: #f8f9fa; color: #222; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==Long-term&#160; (x-risk)==</div></td></tr> </table>

KevinYager