kaivu

Karma: 292

Inverse Rubric Optimization: A testbed for agent science

zef, leni, kaivu and rohuang

11 Jun 2026 1:44 UTC

5 points

0 comments1 min readLW link

(fulcrum.inc)

Tracking Difficulty with Feature Portfolios

kaivu, leni, zef and rohuang

19 May 2026 2:25 UTC

22 points

0 comments5 min readLW link

Benchmarking Real Work

kaivu, leni, rohuang and zef

16 May 2026 20:43 UTC

30 points

2 comments4 min readLW link

The bitter lesson for software

zef, rohuang and kaivu

16 Mar 2026 23:38 UTC

15 points

3 comments2 min readLW link

(fulcruminc.substack.com)

More is different for intelligence

zef, rohuang and kaivu

7 Mar 2026 0:02 UTC

17 points

0 comments2 min readLW link

(fulcruminc.substack.com)

Introducing Lunette: auditing agents for evals and environments

zef, leni and kaivu

15 Dec 2025 23:17 UTC

23 points

0 comments1 min readLW link

(fulcrumresearch.ai)

Automated real time monitoring and orchestration of coding agents

zef, kaivu and leni

23 Oct 2025 22:12 UTC

8 points

0 comments2 min readLW link

(fulcrumresearch.ai)

AI agents and painted facades

leni, zef and kaivu

30 Aug 2025 23:13 UTC

38 points

3 comments2 min readLW link

(fulcrumresearch.ai)

Me, Myself, and AI: the Situational Awareness Dataset (SAD) for LLMs

L Rudolf L, bilalchughtai, Jan Betley, kaivu, Jérémy Scheurer, Mikita Balesni, AlexMeinke, Owain_Evans and Marius Hobbhahn

8 Jul 2024 22:24 UTC

109 points

40 comments5 min readLW link 1 review

Takeaways from a Mechanistic Interpretability project on “Forbidden Facts”

Tony Wang, Miles Wang and kaivu

15 Dec 2023 11:05 UTC

34 points

8 comments10 min readLW link

Update on Harvard AI Safety Team and MIT AI Alignment

Xander Davies, Sam Marks, kaivu, tlevin, leni, maxnadeau and Naomi Bashkansky

2 Dec 2022 0:56 UTC

60 points

4 comments8 min readLW link