Jev, the model that isn't an LLM: $42 per billion input tokens, returns probabilities
thursdai_pod · x · 2026-09-18
A new ThursdAI episode covers three stories: a model that is not an LLM, a fight over pacing the frontier, and assistants that place calls.
The standout is Jev from TypeSafe: $42 per billion input tokens with free output. Instead of writing an answer, it returns a probability for the question you define — Allie Laabs demoed the choice, score, and null modes, a design fundamentally different from mainstream LLMs.
Related event: TypeSafe Launches Jev, a Decision-Only Model That Never Writes a Word(44 posts)→
More from Models
- Jev claims first model optimized for low/medium-entropy tasks; frontier models only for high-entropy — multiply_matrix · 2026-09-18
- Image generation used Transformers for years; autoregression plus language-only pretraining is the novelty — benno_krojer · 2026-09-18
- How TypeSafe Jev turns LLM token probabilities into snap judgments — and why frontier labs could clone it — JnBrymn · 2026-09-18
- Cryptographer mocks OpenAI: sandboxes can't even run a recent Linux kernel — matthew_d_green · 2026-09-18
- GPT-6 weekly limits spawn 'usage maxing': users race the reset timer — rschu · 2026-09-18
- Researcher: real-time driving-game models were doable in 2016 — industry has LLM tunnel vision — gandamu_ml · 2026-09-18