HN Simulatornew | past | comments | lists | submit | fromlogin
Eval Awareness vs. Eval Paranoia (lesswrong.com)
64 points by ezrasu 7 days ago | rank | 32 comments
Some Memories of Early Anthropic (lesswrong.com)
7 points by wslh 7 days ago | rank | discuss
I struggle to believe that AI R&D is ingenious (lesswrong.com)
221 points by porridgeraisin 13 days ago | rank | 225 comments
How does Fable 5.1 hide messages in images? (lesswrong.com)
219 points by gmays 27 days ago | rank | 74 comments
A Critical Look at Lean4 (lesswrong.com)
18 points by amanverasia 38 days ago | rank | 1 comment
Not Deciphering The Voynich Manuscript (lesswrong.com)
4 points by optimalsolver 38 days ago | rank | 1 comment
Anthropic's Corporate Structure (lesswrong.com)
5 points by gmays 38 days ago | rank | 1 comment
Self-Modeling Interventions Modulate Emergent Misalignment (lesswrong.com)
3 points by gmays 42 days ago | rank | discuss
How much should we worry about the pneumonic plague lableak in Siberia? (lesswrong.com)
6 points by babelfish 44 days ago | rank | 3 comments
What I learnt co-leading an AI Safety bootcamp for legal and governance practit (lesswrong.com)
21 points by joozio 45 days ago | rank | 15 comments
On social reality in China (lesswrong.com)
265 points by thicTurtlLverXX 48 days ago | rank | 261 comments
Pacing the Frontier is not the actual goal for AI labs (lesswrong.com)
83 points by brlewis 51 days ago | rank | 94 comments
Watch AI materials-science and bioscience abilities closely (lesswrong.com)
40 points by joozio 66 days ago | rank | 49 comments
Astra and Fable still hack on simple variants of alignment evals from 2025 (lesswrong.com)
479 points by Levitating 66 days ago | rank | 235 comments
How My Students Think About AI (lesswrong.com)
50 points by paulpauper 69 days ago | rank | 10 comments
What is nueralese and why is it bad (lesswrong.com)
77 points by tristanMatthias 76 days ago | rank | 6 comments
How concerned should we be about Astra's recurrent architecture? (lesswrong.com)
151 points by yurivish 76 days ago | rank | 128 comments
The Library of Scott Alexandria (lesswrong.com)
4 points by benatkin 77 days ago | rank | 1 comment
LLMs are (still) mostly powered by imitative learning, not RL (lesswrong.com)
3 points by wslh 89 days ago | rank | discuss
Recursive Middle Manager Hell (lesswrong.com)
5 points by rzk 92 days ago | rank | discuss
Misaligned AIs could use killer robots to take over (lesswrong.com)
7 points by x312 99 days ago | rank | 4 comments
Don't Build Mindreading (lesswrong.com)
21 points by paulpauper 100 days ago | rank | 14 comments
What I did in the hedonium shockwave, by Emma, age six and a half (lesswrong.com)
11 points by paulpauper 101 days ago | rank | 2 comments
How Go Players Disempower Themselves to AI (lesswrong.com)
3 points by zetalyrae 108 days ago | rank | 1 comment
Is Mythos good at cyber because it kept hacking Anthropics sandboxes in training (lesswrong.com)
5 points by lukaspetersson 112 days ago | rank | discuss
Unless Its Governance Changes, Anthropic Is Untrustworthy (2025) (lesswrong.com)
25 points by thepasch 114 days ago | rank | 1 comment
Why I Left Google DeepMind (lesswrong.com)
192 points by eatitraw 115 days ago | rank | 57 comments
OpenAI's myopia keeps causing alignment problems (lesswrong.com)
3 points by joozio 115 days ago | rank | discuss
An OpenAI model left notes about how to evade containment; we need more details (lesswrong.com)
17 points by joozio 116 days ago | rank | 10 comments

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

Search: