Dettmers: CliffCompaction works much better with full thinking traces
Tim_Dettmers · x · 2026-09-23
In his CliffCompaction thread, Tim Dettmers notes the tool works much better with full thinking traces, aligning with what frontier labs say: OpenAI's math and ARC-AGI results largely stem from autocompaction that accounts for thinking traces.
More from coding & agent
- User automates entire video clipping workflow with Nous Research's Hermes agent — Teknium · 2026-11-12
- As models improve, writing good evals gets harder and more important — amankhan · 2026-11-12
- Free AI game jam in SF Nov 14–15 with teams from Anthropic, Google, Meshy, OpenAI — chrisfirst · 2026-11-12
- Omarchy 4.6 lets you share local AI models across your tailnet, says DHH — alexcovo_eth · 2026-11-12
- Coding harnesses hand shell access to inference providers — 4-step gateway mitigation — shensi · 2026-11-12
- Slack's David Hoang: agents beat people on coordination, proposes 'boundary agents' — davidhoang · 2026-11-12