User: ChatGPT agent failed to finish half its workspace tasks after 24 hours
koltregaskes · x · 2026-10-20
A user recalls an AI lab leader saying 'it just works' last year, yet after 2 hours of queued, specific instructions to ChatGPT (connected to Linear) to clean up his workspace, nearly 24 hours later less than half the tasks were done — he now has to ask it to reread his messages and just get things done.
More from Models
- DeepSeek open-sources DeepInfer, the production inference framework behind DeepSeek-V4.1-Flash — deepseek_ai · 2026-10-20
- DeepSeek-V4.1-Flash-1017 Hits Qoder Day One, Free at 0.0x Credits Until Oct 24 — alifcoder · 2026-10-20
- DeepSeek-V4.1-Flash quantized to 2-4 bit mixed precision for dual RTX PRO 6000 with 0.1306 KL divergence — TheZachMueller · 2026-10-20
- Vals AI: DeepSeek V4.1 Flash Beats GPT-6 Sol on Offensive Cybersecurity Benchmark — Hesamation · 2026-10-20
- MemTensor releases MemT-1.0, a memory-native architecture embedding continuous memory into model computation — MemTensor · 2026-10-20
- mitsuhiko: Opus 5.5 is such a good writer that reading its reports is now a joy — mitsuhiko · 2026-10-20