OpenAI says Sol usage now lasts 18% longer after fixing tool-heavy workflows
soumitrashukla9 · x · 2026-07-30
An OpenAI-linked update says Sol usage should now last about 18% longer in typical use, with even larger gains for some power users.
The team says Sol had been burning through Codex limits faster than expected because it works longer, calls more tools, and pushes harder on difficult tasks.
To fix that, they improved efficiency around tool waits and large web searches, reset usage limits for ChatGPT Work and Codex users, and said the temporary five-hour limit will return the next day.
More from Models
- Kimi K3 Lands in Japan via ai& Inference, Undercutting Claude Opus 5 Costs — DavidBennett__ · 2026-07-30
- Verdent Partners with Moonshot to Deeply Optimize Kimi K3 for Agentic Coding — eyishazyer · 2026-07-30
- Test Shows Claude Code Consumes 6x More Tokens Per Task Than Kimi Code — zainhas · 2026-07-30
- Kimi K3 vs GPT-5.6: Generating Playable Games with Working Combat Systems — aftahi_ai · 2026-07-30
- Local RAG Resilience Tested: Llama Holds Firm, Mistral Folds to Poisoned Data — arcandor · 2026-07-30
- LLM Tool Calls Are the New Black Box: Can Models Restrain Unnecessary Calls? — NickPassig · 2026-07-30