Context Window Strategy Differences: OpenAI vs Anthropic
PawelHuryn · x · 2026-07-20
Hacker News found that OpenAI quietly reduced GPT-5.6 Sol's max context window by 100k tokens (to 272k) in a code tool PR, labeling it a 'bug fix'.
In contrast, Anthropic took the opposite approach: retaining up to 1 million context window in Cowork, without providing a /compact compression command, instead restricting model usage itself.
Related event: OpenAI Quietly Cuts Codex Context Window to 272k Tokens(5 posts)→
More from Models
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11