GPT-6.1 Sol ran in circles for days on ts-rust, sparking regression complaints
karmay007 · x · 2026-09-30
Reacting to @theo's progress post on his Rust project ts-rust, karmay007 highlights that GPT-6.1 Sol was thrown at the task for several days and "ran in circles and made no progress." He concludes that 5.6 Sol outperforms both 6.0 and 6.1 Sol, quipping that "we are officially REGRESSING" — a notable counterpoint to the newest model's positioning.
More from coding & agent
- DeepSeek quietly ships Harness GUI desktop app with PTC orchestration and plugin architecture — solyarisoftware · 2026-09-30
- Opus 5.5 with auto permissions wiped dev's entire $home, deleting ~/.codex and ~/.claude — PawelHuryn · 2026-09-30
- TIRx Harness turns AI agents into GPU kernel engineers, with up to 6.84x speedups — JiaZhihao · 2026-09-30
- GPT-6.1 Sol ships in GitHub Copilot with far fewer tokens and steps per task — DanWahlin · 2026-09-30
- How Clay uses LangSmith to debug why its AI agent got it wrong — LangChain · 2026-09-30
- Goldman Sachs Deploys Agentic AI Alongside Thousands of Human Software Engineers — rvp · 2026-09-30