TypeSafe's Jev isn't an LLM: it returns calibrated probabilities with free output
altryne · x · 2026-09-19
altryne adds that TypeSafe's Jev is not an LLM: you define the question and it returns a calibrated probability instead of writing paragraphs. Combined with pricing of $42 per billion input tokens and free output, it's a notably different product shape — you pay for the question, not the answer.
Related event: TypeSafe Jev Is Not an LLM: Charges per Input, Output Free(2 posts)→
More from Models
- TypeSafe AI's RLCD post-training路线挑战 RLHF 正统,引发关注 — FrankFelixAI · 2026-09-19
- Router flaw spotted: it picks models but never grades answers — grade-then-escalate fix proposed — airesearch12 · 2026-09-19
- Every frontier lab is having an urgent 'Jev' meeting today, observer says — altryne · 2026-09-19
- Jev classifies the entire Bluesky firehose for animal posts in near real time — danshipper · 2026-09-19
- Critics say OpenAI's eval environments aren't airgapped and barely monitored — MoonL88537 · 2026-09-19
- Codex Reset Coupon Changes Usage Reset Cycle, User Flags Billing Quirk — algo_diver · 2026-09-19