GPT-6 best-ever at math but crippled by tiny context; Fable 5.1 still owns long agentic work
MParakhin · x · 2026-09-06
Former Microsoft Bing engineering VP Mikhail Parakhin shares hands-on impressions after heavy use of GPT-6 and Fable 5.1:
- GPT-6 Max is the best model he's ever used for math/ML, beating 5.2 Pro; a 6 Pro tier appeared in the web interface this morning
- But GPT-6's tiny context window hampers it badly — he likens it to "talking to a super-smart Dory"
- Fable 5.1 remains best at long agentic tasks: better instruction-following and more elegant coding solutions
His workflow has inverted: he develops solutions with GPT-6, then polishes code and runs experiments with Fable 5.1.
Related event: GPT-6 Tops Math but Small Context Hurts Long Tasks(4 posts)→
More from Models
- Meta researcher: horrifying infra, not talent, is why OSS can't catch closed frontier — A_K_Nain · 2026-10-23
- TypeSafe's Jev: a "Decision Model" LLM That Returns Floats at $0.042/M Input Tokens — ariG23498 · 2026-10-23
- Microsoft's MAI-Base-2 scaling ladder pegs the L42 run at ~1.8×10^23 FLOPs — teortaxesTex · 2026-10-23
- Local model agentic coding benchmark: 27B matches 125B, tool-calling is the lever — Joralk_ · 2026-10-23
- NVIDIA open-sources PersonaPlex-7B, a full-duplex voice AI model that listens and talks simultaneously — solyarisoftware · 2026-10-23
- NVIDIA's KumoRFM-2: a foundation model that predicts churn, fraud and demand straight from relational databases — solyarisoftware · 2026-10-23