GPT vs Claude: Context Window Strategy Divergence
PawelHuryn · x · 2026-07-20
Hacker News discovered that GPT-5.6 Sol's max context window in Codex was quietly reduced by 100k tokens to 272k tokens, labeled as a bug fix in release notes.
The author finds this puzzling because Anthropic took the opposite approach: retaining a 1 million context window in Cowork without a /compact command, instead restricting the model itself.
Related event: OpenAI Quietly Reduces Codex Context Window to 272k Tokens(5 posts)→
More from Models
- Grok 4.5 is now free inside Cursor, the popular AI coding IDE — mark_k · 2026-07-21
- GPT often converges on the same near-miss ideas in math problems — yacineMTB · 2026-07-21
- Eno Reyes says model distillation is basically unstoppable — LangChain · 2026-07-21
- Sakana says multiple diffusion models plus MCTS beat test-time scaling on coding and math — SakanaAILabs · 2026-07-21
- OpenAI hackathon project stalls as Codex struggles on voice, while Claude spots the issue — ColleenMBrady · 2026-07-21
- Kimi K3 lands exactly on China’s 2-year AI capability trend line — peterwildeford · 2026-07-21