# sources

[Corpus index](../index.txt)

- [Bioshok vs Akira P(doom)徹底討論書き起こし(修正なし全文)](../sources/agi_hub.pdoom-debate-1-transcript.txt)
- [X @Align_ASI post 2055116276960559467](../sources/akira.x.2055116276960559467.txt)
- [X @Align_ASI post 2055116279485489376](../sources/akira.x.2055116279485489376.txt)
- [X @Align_ASI post 2055121067929489784](../sources/akira.x.2055121067929489784.txt)
- [X @Align_ASI post 2055466196200505634](../sources/akira.x.2055466196200505634.txt)
- [X @Align_ASI post 2055571488686674072](../sources/akira.x.2055571488686674072.txt)
- [X @Align_ASI post 2056249992826982411](../sources/akira.x.2056249992826982411.txt)
- [X @Align_ASI post 2056298561248039229](../sources/akira.x.2056298561248039229.txt)
- [X @Align_ASI post 2056306172353991103](../sources/akira.x.2056306172353991103.txt)
- [X @Align_ASI post 2056653057535205557](../sources/akira.x.2056653057535205557.txt)
- [X @Align_ASI post 2056653932890583189](../sources/akira.x.2056653932890583189.txt)
- [X @Align_ASI post 2056760361928519950](../sources/akira.x.2056760361928519950.txt)
- [X @Align_ASI post 2087017636877996133](../sources/akira.x.2087017636877996133.txt)
- [The Problem](../sources/bensinger_et_al.the-problem.txt)
- [Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs](../sources/betley_et_al.emergent-misalignment.txt)
- [AGIがもたらす産業・技術爆発](../sources/bioshok.agi-industrial-tech-explosion.txt)
- [AI安全性と国家安全保障の対立](../sources/bioshok.ai-safety-vs-national-security.txt)
- [The Superintelligent Will: Motivation and Instrumental Rationality in Advanced Artificial Agents](../sources/bostrom.superintelligent-will.txt)
- [Automated alignment is harder than you think](../sources/bowkis_et_al.automated-alignment-harder-than-you-think.txt)
- [Scheming AIs: Will AIs fake alignment during training in order to get power?](../sources/carlsmith.scheming-ais.txt)
- [A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders](../sources/chanin_et_al.a-is-for-absorption.txt)
- [My views on “doom”](../sources/christiano.my-views-on-doom.txt)
- [Takeoff speeds](../sources/christiano.takeoff-speeds.txt)
- [What failure looks like](../sources/christiano.what-failure-looks-like.txt)
- [Where I agree and disagree with Eliezer](../sources/christiano.where-i-agree-and-disagree-with-eliezer.txt)
- [ARC's first technical report: Eliciting Latent Knowledge](../sources/christiano_xu.arcs-first-technical-report-eliciting-latent-knowledge.txt)
- [Should Artificial Intelligence Governance be Centralised? Design Lessons from History](../sources/cihon_et_al.should-ai-governance-be-centralised.txt)
- [#235 – Ajeya Cotra on whether it’s crazy that every AI company’s safety plan is ‘use AI to make AI safe’](../sources/cotra_wiblin.80000-hours-crunch-time.txt)
- [What a compute-centric framework says about AI takeoff speeds](../sources/davidson.compute-centric-framework-ai-takeoff.txt)
- [Scaling Laws For Scalable Oversight](../sources/engels_et_al.scaling-laws-for-scalable-oversight.txt)
- [Most AI value will come from broad automation, not from R&D](../sources/erdil_barnett.most-ai-value-broad-automation.txt)
- [Will AI R&D Automation Cause a Software Intelligence Explosion?](../sources/eth_davidson.ai-r-and-d-automation-software-intelligence-explosion.txt)
- [Current AIs seem pretty misaligned to me](../sources/greenblatt.current-ais-seem-pretty-misaligned.txt)
- [Jankily controlling superintelligence](../sources/greenblatt.jankily-controlling-superintelligence.txt)
- [Alignment faking in large language models](../sources/greenblatt_et_al.alignment-faking-large-language-models.txt)
- [Risks from Learned Optimization in Advanced Machine Learning Systems](../sources/hubinger_et_al.risks-from-learned-optimization.txt)
- [Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training](../sources/hubinger_et_al.sleeper-agents.txt)
- [How Afraid of the A.I. Apocalypse Should We Be?](../sources/klein_yudkowsky.how-afraid-of-ai-apocalypse.txt)
- [A sketch of an AI control safety case](../sources/korbak_et_al.ai-control-safety-case.txt)
- [Sparse Autoencoders Do Not Find Canonical Units of Analysis](../sources/leask_et_al.sparse-autoencoders-do-not-find-canonical-units-of-analysis.txt)
- [Natural Emergent Misalignment from Reward Hacking in Production RL](../sources/macdiarmid_et_al.natural-emergent-misalignment-reward-hacking.txt)
- [The Alignment Problem from a Deep Learning Perspective](../sources/ngo_et_al.alignment-problem-deep-learning.txt)
- [Weak-to-strong generalization](../sources/openai.weak-to-strong-generalization.txt)
- [Why Corrigibility is Hard and Important (i.e. "Whence the high MIRI confidence in alignment difficulty?")](../sources/raemon_yudkowsky_soares.corrigibility-hard-important.txt)
- [Computing Power and the Governance of Artificial Intelligence](../sources/sastry_et_al.computing-power-and-governance-of-ai.txt)
- [An International Agreement to Prevent the Premature Creation of Artificial Superintelligence](../sources/scher_et_al.international-agreement-prevent-premature-asi.txt)
- [A central AI alignment problem: capabilities generalization, and the sharp left turn](../sources/soares.sharp-left-turn.txt)
- [Optimal Policies Tend to Seek Power](../sources/turner.optimal-policies-tend-to-seek-power.txt)
- [Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization](../sources/yang_et_al.superficial-alignment.txt)
- [AGI Ruin: A List of Lethalities](../sources/yudkowsky.agi-ruin.txt)
- [Artificial Intelligence as a Positive and Negative Factor in Global Risk](../sources/yudkowsky.ai-positive-negative-factor.txt)
- [Autonomous AGI](../sources/yudkowsky.autonomous-agi.txt)
- [Coherent Extrapolated Volition](../sources/yudkowsky.coherent-extrapolated-volition.txt)
- ['Empiricism!' as Anti-Epistemology](../sources/yudkowsky.empiricism-as-anti-epistemology.txt)
- [Irretrievability; or, Murphy's Curse of Oneshotness upon ASI](../sources/yudkowsky.irretrievability.txt)
- [There's No Fire Alarm for Artificial General Intelligence](../sources/yudkowsky.no-fire-alarm-for-agi.txt)
- [Orthogonality Thesis](../sources/yudkowsky.orthogonality-thesis.txt)
- [Pivotal act](../sources/yudkowsky.pivotal-act.txt)
- [Security Mindset and the Logistic Success Curve](../sources/yudkowsky.security-mindset-logistic-success-curve.txt)
- [Security Mindset and Ordinary Paranoia](../sources/yudkowsky.security-mindset-ordinary-paranoia.txt)
- [Shah and Yudkowsky on alignment failures](../sources/yudkowsky.shah-alignment-failures.txt)
- [Pausing AI Developments Isn't Enough. We Need to Shut it All Down](../sources/yudkowsky.shut-it-all-down.txt)
- [The Sun is big, but superintelligences will not spare Earth a little sunlight](../sources/yudkowsky.sun-is-big.txt)
- [Will superintelligent AI end the world?](../sources/yudkowsky.ted-superintelligent-ai.txt)
- [Thou Art Godshatter](../sources/yudkowsky.thou-art-godshatter.txt)
- [Value is Fragile](../sources/yudkowsky.value-is-fragile.txt)
- [Ngo and Yudkowsky on alignment difficulty](../sources/yudkowsky_ngo.alignment-difficulty.txt)
- [Why not just read the AI's thoughts?](../sources/yudkowsky_soares.read-ai-thoughts.txt)