Trained a Jev-style API with one prompt: 16 min on an A100, ~$6.60 total
maximelabonne · x · 2026-10-01
After OpenAI, Liquid and Nace shipped Jev-style APIs this week, Maziyar Panahi trained his own with a single prompt in HuggingChat. An agent fine-tuned it on an NVIDIA A100 in 16 minutes, fixing its own bugs along the way: the full 60K version cost $6.60 and picked the right tool 62% of the time out of 20 options. Maxime Labonne (Hugging Face) amplified it.
Related event: Developer Trains 150M-Param Routing Model with One Prompt for $6.60(3 posts)→
More from coding & agent
- Firecrawl launches People Enrichment Pack so agents can find buyers, talent and company data — devdigest · 2026-10-02
- Stanford launches CS 224V, an Agentic AI course tackling agent reliability with RAG and formal methods — stanfordnlp · 2026-10-02
- Early Hands-On: OpenAI's Dots Agent Impresses With Speed and First-Try Accuracy — billyjhowell · 2026-10-02
- MINTEval, accepted at NeurIPS, shows LLM agents fail at tracking evolving contexts — EliasEskin · 2026-10-02
- Claude Code lead on the sassy status dot: it might just be busy with something else — cyrus_zei · 2026-10-02
- LlamaIndex Launches Extract v2.5, Beats Claude and GPT at 30%-4x Lower Cost — llama_index · 2026-10-02