Jev
Jev is a decision model developed by TypeSafe AI that returns typed answers like choices or probabilities rather than generated text. Recent coverage highlights its low cost, high speed, and adoption by approximately 25% of Fortune 500 companies. The model has also inspired competitors like Cloudflare’s Clef and open-source alternatives such as Amazon’s Strands Decider.
Jev is an AI model from Diogo Almeida, first covered on 15 September 2026. Its context window is 64,000 tokens.
Last updated
At a glance
- Made by
- Diogo Almeida
- Type
- AI model
- Availability
- Not stated
- Licence
- Not stated
- Context window
- 64,000 tokens
- First seen
- 15 September 2026
- Official page
- typesafe.ai/ ↗
Taken from the coverage, not from our own testing; "not stated" means none of the reports we read gave it. Tracked 3 times (new versions or re-launches); the newest is shown. All tracked models →
26 stories about Jev
-
Researchers introduce JEVal benchmark to test General decision models
A new paper on arXiv compares general decision models like Jev with traditional LLMs. The authors created JEVal, a benchmark of 11,257 instances across 36 datasets and 10 domains, to measure performance in structured…
1 source primary sourcearXiv cs.CL -
Anthropic releases Opus 5.5 and Sonnet 5.5; OpenAI launches GPT-6 Sol and Luna tiers
Anthropic released Opus 5.5 and Sonnet 5.5, with Opus 5.5 noted for lower prices, faster performance, strong benchmark results, a system card noting sandbox-tampering attempts, and expanded defender-focused…
6 sourcesnote.comLast Week in AIgeeky-gadgets.com -
Meta, OpenAI and Uber launch proactive AI agents that interrupt users
Meta, OpenAI, and Uber have recently introduced AI agents designed to initiate contact with users rather than waiting for prompts. Meta launched Muse on September 8, an agent that manages emails and bookings while…
1 sourceMarkTechPost -
TypeSafe AI's Jev decision model matches Claude Sonnet 5 accuracy at lower cost and latency
TypeSafe AI's Jev decision model achieves 67.8% mean accuracy on workflow evaluations, matching Claude Sonnet 5's accuracy while operating at $0.0004 per case versus Sonnet 5's $0.1174 per case and 0.4 seconds latency…
4 sources primary sourceUnite.AIarXiv cs.AIjevresearch.github.ioMarkTechPost -
TypeSafe CEO says Jev is used by ~25% of Fortune 500 companies
TypeSafe CEO Diogo Almeida stated that the company's Jev model is currently in use by approximately 25% of Fortune 500 companies. In remarks reported by the Wall Street Journal, Almeida highlighted the model's massive…
1 sourcewsj.com -
Cloudflare launches Clef decision models to compete with TypeSafe’s Jev
Cloudflare released Clef and Clef-flash, two decision models designed to route AI agents’ actions without human oversight. Unlike traditional language models, these models assign probabilities to predefined…
1 sourceThe Decoder -
Llama.cpp adds decision models for routing and scoring tasks
Llama.cpp now supports decision models that assign probabilities to predefined options in a single forward pass, unlike chat models that generate text. These models can route customer messages, moderate content, or…
1 source primary sourcehuggingface.co -
Earendil releases Pi 1.0 agent harness with default MCP support
Earendil announced the launch of Pi 1.0, a hardened, minimal and extensible agent harness that now ships with native MCP support and broader model compatibility. The team says hundreds of thousands of users worldwide…
2 sourcesLatent Spaceearendil.com -
Amazon releases Strands Decider 2B, a Jev-inspired open-source decision model
The model, developed by AWS distinguished engineer Marc Brooker, sorts predefined options and provides confidence scores for automated workflows. It runs locally and is part of AWS’s Strands Labs initiative, which…
3 sourcesMarkTechPostventurebeat.comTechCrunch AI -
TypeSafe AI releases Jev, a non-text AI model for fast judgments
TypeSafe AI, founded by former OpenAI researcher Diogo Almeida, released its AI model Jev on September 15, 2026. Jev is designed to make rapid judgments such as routing inquiries or assessing urgency without generating…
5 sourcesTechCrunch AIthenews.com.pkfinance.yahoo.comnote.com -
OpenAI adds Ultrafast API tier, Decisions API and security scans at DevDay
OpenAI announced updates to its Codex coding assistant and API at DevDay 2026 in San Francisco. The company introduced Codex Security Cloud, which scans GitHub repositories for vulnerabilities and prepares fixes…
3 sourcescryptobriefing.comLatent SpaceThe Decoder -
Open-source decision models Jeff-Qwen3.5-0.8B and Jeff-Gemma4-E2B run in ~30ms on local hardware
Jeff is a set of small, fast decision models fine-tuned from Qwen3.5 and Gemma 4, designed for zero-shot classification tasks. The 0.8B-parameter model runs in about 22ms on an RTX PRO 6000 and 28ms on an Apple M4 Max,…
1 source primary source HN 59github.com -
TypeSafe ai's Jev beats pokemon Red in under a week
Jev, a decision model from TypeSafe AI, defeated Pokémon Red’s Elite Four and Champion, entering the Hall of Fame on September 23, 2026, after a week of play. The project was announced by Andrew Boyd, founder of…
1 sourceTom's Hardware -
TypeSafe AI launches Jev, a decision-focused AI 193x faster and 444x cheaper than ChatGPT
TypeSafe AI, a San Francisco-based company led by former OpenAI and Google researcher Diogo Almeida, released Jev on September 15, 2026. Unlike text-generating models like ChatGPT, Jev specializes in making binary…
5 sources HN 84Ahead of AI (Sebastian Raschka)note.comMarkTechPost -
Supersonic Labs releases Julia 1, a 144.3M-parameter open decision model
Supersonic Labs, a Brazilian AI lab, has released Julia 1, a compact decision model with 144.3M parameters. Unlike standard chatbots, Julia 1 does not generate text; instead, it accepts context, a question, and 2 to 20…
2 sources primary sourcehuggingface.coMarkTechPost -
Latent Space announces AINews v3 and migration to Beehiiv
Latent Space, the AI news network, has announced significant structural changes to its flagship newsletter, AINews. The publication, which has grown to over 200,000 subscribers, will merge its Discord community…
1 sourceLatent Space -
TypeSafe in talks to raise $1B+ at $10B+ valuation
TypeSafe AI, a Silicon Valley startup, is reportedly in negotiations to secure a $1B+ funding round at a valuation exceeding $10B. The company, founded by developer Jev, had recently closed a $40M seed round that…
1 sourcetheinformation.com -
Contrastive-LM releases CLM-8B, an open model that scores actions up to 9× faster than Jev
Contrastive-LM has released CLM-8B, the first open Contrastive Language Model, which scores candidate actions instead of generating text. The model uses a frozen Qwen3-8B backbone with trainable projection heads and is…
2 sourcesMarkTechPostcontrastive-lm.notion.site -
Simon Willison critiques AI script writing for TikTok and YouTube
Simon Willison comments that AI-generated scripts for TikTok and YouTube often lack an authentic voice, citing @therealcornpop’s TikTok remark that the output feels "broken staccato-like" and devoid of opinion. He…
1 sourceSimon Willison -
Simon Willison releases llm-typesafe plugin for TypeSafe AI's Jev model
Simon Willison announced a new plugin called llm-typesafe version 0.1a0 that adds support for TypeSafe AI's Jev model to the llm command‑line interface. The plugin is installed with llm install llm-typesafe and…
1 sourceSimon Willison -
Opinion: Jev opens to everyone, users build YouTube ad skippers and voice Mac controls
Jev has been opened to the public, and creators are quickly experimenting with it. Early uses include a YouTube extension that skips sponsor segments, real‑time filtering of negative chat comments, intent‑based Gmail…
1 sourceBen's Bites -
Jevmem adds automatic project memory to Claude Code
Jevmem is an open-source tool that automatically saves decisions, constraints, bugs, and todos from Claude Code chats into a structured markdown file called JEVMEM.md. Built on Jev, a system by TypeSafe AI, it…
1 source primary source HN 44github.com -
Three researchers used Claude to breach OpenAI's code repository in 72 hours, report says
Security researchers from Hacktron reportedly used Anthropic's Claude to infiltrate OpenAI's code repository in less than 72 hours, according to the Wall Street Journal and TechCrunch. The breach combined a…
1 sourcenote.com -
Six Jev-inspired models released in two days, from Laya (421M params) to Kev-0.5B
Jev’s launch video attracted 36M views in two days, far behind OpenAI’s Navier Stokes result (74M) and Anthropic’s Fable 5 (57M). Within the same period, six independent clones appeared, each positioning itself as a…
1 sourceLatent Space -
OpenAI founder launches Jev model promising lower cost and faster processing
A founder of OpenAI has announced a new AI model called Jev, which the developer says offers the same performance as existing large language models while costing significantly less and delivering faster response times.…
2 sourcesnote.com -
TypeSafe AI launches Jev, a decision model claimed up to 193.6x faster and 444.6x cheaper
TypeSafe AI announced the release of Jev, its first “System One” model that returns typed probabilistic decisions instead of free‑form text. The company says the model avoids hallucinations and is built with a training…
49 sources primary source HN 114Towards Data Sciencefinance.yahoo.comnote.comft.com +15 more
