Jev vs tabular foundation models: zero-shot decision routing is not grounded prediction
Arindam_1729 · x · 2026-10-17
The author clears up a common confusion between Jev and tabular foundation models (TFMs) like TabPFN:
- Jev: unstructured in → structured out. Zero-shot classification and decision routing—worth pursuing a lead? reply to an email? which agent handles a task? No task-specific training data, lightweight and cheap.
- TFM: structured data in → grounded predictions out, learning patterns from tabular examples.
The quoted article notes Jev came out of stealth on Sept 15 and within two weeks developers were routing real traffic through it, with OpenAI and AWS shipping their own decision models; it walks through building a Jev-like decision model in 15 minutes.
More from coding & agent
- Open-source Claude Code skill embeds a live website inside a tweet via player cards — doooyle · 2026-10-17
- YC Partner: Personal Software Is Cheaper Than Ever, and Open-Sourced Code Lets Others' Agents Fill the Gaps — ycombinator · 2026-10-17
- Claude Code's contextual UX hints earn praise from a heavy daily user — iamsahaj_xyz · 2026-10-17
- Codex-created worktrees blamed for killing a 600GB-battered SSD; users say disk bloat is the worst part of AI coding tools — natesiggard · 2026-10-17
- Engineer: I'm not smarter than AI anymore — time to learn to orchestrate it — KevinNaughtonJr · 2026-10-17
- Open-source OODA pentest agent drives Kali and Playwright tools directly over MCP — irraz_rulez · 2026-10-17