Intelligence Yield — METR Time Horizons v1.1

kept by eddie feb 25

Opus 4.6 delivers 14 times more useful work per compute-minute than Codex 5.3, a metric called Intelligence Yield derived from METR Time Horizons data.

The Big-O Complexity of Vibe Coders — Shiveesh Fotedar
As vibe coding scales in companies, evaluation will shift from raw speed to token efficiency, treating prompts like algorithms with measurable Big-O complexity.
also on #efficiency
GPT-5.3-Codex | Hacker News
OpenAI releases GPT-5.3-Codex, a faster agentic coding model that achieves state-of-the-art results on SWE-Bench Pro and Terminal-Bench 2.0.
also on Opus 4.6, #benchmarks, #ai-research
What I learned this week - Pretraining parallelisms, Can distillation be stopped, Mythos and the cybersecurity equilibrium, Pipeline RL, On why pretraining runs fails
A set of rough notes exploring challenges in AI model distillation, cybersecurity offense/defense dynamics, and pipeline RL for training.
also on Opus 4.6, #ai-research
How far behind are open models? — LessWrong
Open models lag behind closed frontier models by 8–10 months on private benchmarks and 4–6 months on public, with the gap growing since DeepSeek R1.
also on METR, #benchmarks, #ai-research
How Do You Measure an A.I. Boom? - The New York Times
A chart from the nonprofit METR has become an industrywide obsession for measuring the rapid development of large AI systems.
also on METR, #benchmarks, #ai-research