Hacker Newsnew | past | comments | ask | show | jobs | submit | fromlogin
Shutdown Resistance in Reasoning Models (lesswrong.com)
1 point by ben_w 14 hours ago | past | discuss
A path from autonomy V&V to AGI alignment? (lesswrong.com)
1 point by yoav_hollander 2 days ago | past | discuss
Race and Gender Bias as an Example of Unfaithful Chain of Thought in the Wild (lesswrong.com)
9 points by ibobev 3 days ago | past | discuss
Dialects for Humans: Sounding Distinct from LLMs (lesswrong.com)
5 points by nebrelbug 3 days ago | past | 1 comment
Proposal for making credible commitments to AIs (lesswrong.com)
1 point by surprisetalk 5 days ago | past | discuss
Machines of Faithful Obedience – LessWrong (lesswrong.com)
1 point by kiyanwang 5 days ago | past | discuss
X explains Z% of the variance in Y (lesswrong.com)
15 points by ibobev 7 days ago | past | 1 comment
X explains Z% of the variance in Y (lesswrong.com)
4 points by surprisetalk 8 days ago | past | discuss
A case for courage, when speaking of AI danger (lesswrong.com)
2 points by ibobev 9 days ago | past | discuss
The Best of LessWrong (lesswrong.com)
3 points by sebg 10 days ago | past | discuss
Situational Awareness: A One-Year Retrospective (lesswrong.com)
2 points by fofoz 10 days ago | past | discuss
The V&V method – A step towards safer AGI (lesswrong.com)
1 point by yoav_hollander 11 days ago | past | discuss
My Pitch for the AI Village (lesswrong.com)
1 point by ibobev 11 days ago | past | discuss
Foom and Doom 1: "Brain in a box in a basement" (lesswrong.com)
1 point by ibobev 11 days ago | past | discuss
Metaprogrammatic Hijacking: A New Class of AI Alignment Failure (lesswrong.com)
1 point by Hiyagann 12 days ago | past | discuss
Orienting Towards Wizard Power (lesswrong.com)
1 point by desmondwillow 12 days ago | past | discuss
A deep critique of AI 2027's bad timeline models (lesswrong.com)
90 points by paulpauper 13 days ago | past | 61 comments
X explains Z% of the variance in Y (lesswrong.com)
5 points by kmm 15 days ago | past
Does RL Incentivize Reasoning Capacity in LLMs Beyond the Base Model? (lesswrong.com)
2 points by fzliu 15 days ago | past
A deep critique of AI2027s bad timeline models (lesswrong.com)
5 points by iNic 16 days ago | past | 1 comment
A Technique of Pure Reason (lesswrong.com)
2 points by ibobev 17 days ago | past
Intelligence Is Not Magic, But Your Threshold For "Magic" Is Pretty Low (lesswrong.com)
4 points by optimalsolver 20 days ago | past
Beware General Claims about "Generalizable Reasoning Capabilities" of AI Systems (lesswrong.com)
3 points by mkl 21 days ago | past
A Straightforward Explanation of the Good Regulator Theorem (lesswrong.com)
49 points by surprisetalk 22 days ago | past | 5 comments
Corporations as Paperclip Maximizers (lesswrong.com)
12 points by busssard 23 days ago | past | 9 comments
Broad-Spectrum Cancer Treatments (lesswrong.com)
2 points by surprisetalk 25 days ago | past
Read the Pricing First (lesswrong.com)
2 points by surprisetalk 26 days ago | past
Repairing Yudkowsky's anti-zombie argument (lesswrong.com)
4 points by Bluestein 26 days ago | past
Reference Works for Every Subject (lesswrong.com)
4 points by surprisetalk 30 days ago | past
A Technique of Pure Reason (lesswrong.com)
4 points by ibobev 31 days ago | past

Consider applying for YC's Fall 2025 batch! Applications are open till Aug 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: