Jack&Jill Matches Closed-Model Quality with Together AI's Open-Model Post-Training
togethercompute · x · 2026-10-30
Jack&Jill used Together AI's Post-Training service (RL/SFT) to train a model predicting which candidates a hiring manager will want to meet — a core step in Jill's search. Per founding engineer Oliver Normand, offline evals matched a closed-source model's quality using a significantly cheaper open-source model to serve, with Together's forward-deployed engineers writing scripts to reach first results.
More from coding & agent
- Skyworks cuts root cause analysis from 20 days to 10 with LangGraph agents — LangChain · 2026-10-30
- 73-entry list sorts agent infra: which MCP tools an agent can provision itself vs needs a human — Total-Reasonable · 2026-10-30
- YC-backed Turnstone turns your existing AI subscriptions into an agent team that auto-switches when limits run out — ycombinator · 2026-10-30
- The simple self-testing loop behind every RL data company, per practitioners — teodorio · 2026-10-30
- 7 AI models all faked completion reviewing the same 111k-line codebase — a postmortem — rseroter · 2026-10-30
- Supabase mistook thousands of new databases per minute for a DDoS — it was Lovable integrating silently — alifcoder · 2026-10-30