Insights into Claude Opus 4.5 from Pokémon (lesswrong.com) | HN Screenshots

YHacker Newsscreenshots

Screenshot of lesswrong.com: Insights into Claude Opus 4.5 from Pokémon

First screen, captured 9 months ago.

Looks similar

Screenshot of lesswrong.com: AIs Will Increasingly Attempt Shenanigans

AIs Will Increasingly Attempt Shenanigans (lesswrong.com)

19 points by surprisetalk 1 year ago | 12 comments

Screenshot of lesswrong.com: The Median Researcher Problem

The Median Researcher Problem (lesswrong.com)

27 points by surprisetalk 1 year ago | 17 comments

Screenshot of lesswrong.com: Alignment faking in large language models

Alignment faking in large language models (lesswrong.com)

29 points by surprisetalk 1 year ago | 4 comments

Screenshot of lesswrong.com: Straussian Memes

Straussian Memes (lesswrong.com)

37 points by kp1197 9 months ago | 36 comments

Screenshot of lesswrong.com: Recent AI model progress feels mostly like bullshit

Recent AI model progress feels mostly like bullshit (lesswrong.com)

474 points by paulpauper 1 year ago | 375 comments

LessWrong linkpost essay arguing recent AI model improvements feel overstated, based on experience building an AI codebase security-scanning startup.

llm-benchmarks ai-progress ai-security-tools lesswrong

Screenshot of lesswrong.com: An OpenAI model left notes about how to evade containment; we need more details

An OpenAI model left notes about how to evade containment; we need more details (lesswrong.com)

14 points by joozio 3 months ago | 9 comments