ARC progress update: Competing with sampling — LessWrong
lesswrong.com · 6,287 words · saved by 2 readers
In 2025, the Alignment Research Center (ARC) has been making conceptual and theoretical progress at the fastest pace that I've seen since I first int…
x ARC progress update: Competing with sampling — LessWrong Alignment Research Center (ARC) AI Frontpage 2025 Top Fifty: 11 % 132 ARC progress update: Competing with sampling by Eric Neyman , Victor Lecomte , Wilson Wu , Mikewins , Jacob_Hilton , George Robinson 18th Nov 2025 25 min read 11 132 In 2025, the Alignment Research Center (ARC) has been making conceptual and theoretical progress at the fastest pace that I (Eric) have seen since I first interned in 2022. Most of this progress has come about because of a re-orientation around a more specific goal: outperforming random sampling when it
saved by
related reading
- Competing with sampling — Alignment Research Centeralignment.org
- AlgZoo: uninterpreted models with fewer than 1,500 parameters — LessWronglesswrong.com
- Formal verification, heuristic explanations and surprise accounting — Alignment Research Centeralignment.org
- A Mike's-Eye View of ARC's Research — Alignment Research Centeralignment.org
- The nature of LLM algorithmic progress (v2) — LessWronglesswrong.com
- Alignment Research Centeralignment.org
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- Alignment is not solved but it increasingly looks solvablealigned.substack.com
- Investigating the learning coefficient of modular addition: hackathon project — LessWronglesswrong.com
- Attribution-based parameter decomposition — LessWronglesswrong.com
- I am worried about near-term non-LLM AI developments — LessWronglesswrong.com
- My picture of the present in AI — LessWronglesswrong.com