JEV
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 45
- Unsloth releases free notebook to train decision models locally
Unsloth published a free Colab notebook and companion guide showing how to train Qwen3.5-4B locally into a “decision model” that outputs decisions instead of text, using only 8GB of VRAM. Unsloth says its open-source repo can turn any model, such as Qwen3.8 or Gemma 4, into a decision model, and claims it raised Qwen3.5 0.8B’s aggregate accuracy from 20.7% to 74.3% across three decision benchmarks on just 4GB of VRAM (these figures are Unsloth’s own and the benchmark methodology was not disclosed). The walkthrough covers data preparation (state, questions, gold answers), training and serving, and likens the result to Jev.
UnslothAI (X) · 🔥 0 - Jev maker TypeSafe AI raises $870M at $7.5B valuation led by a16z
TypeSafe AI, the startup behind the Jev model, said it raised about $870 million in a Series A led by Andreessen Horowitz, with Sequoia Capital and existing investor DCVC participating, at a roughly $7.5 billion valuation; Martin Casado is joining the board. The company describes Jev, which went viral after its September 15 release, as built on a transformer architecture but not a large language model: instead of producing text it outputs probabilities, which TypeSafe AI calls “calibrated decisions,” and the company claims it runs faster and uses far fewer tokens than LLMs. TypeSafe AI also says about a third of Fortune 500 companies are already using Jev, a figure it has not detailed or independently verified.
Bloomberg Technology · 🔥 0 - LangChain adds Slack emoji reactions API to Managed Deep Agents
A LangChain blog post says Managed Deep Agents v0.9 adds a reactions attribute for Slack channels that accepts either an emoji string or a callable returning one, so agents can show acknowledgement and loading states during long-running tasks. Developers can use simple heuristics or decision models such as Jev to pick an emoji, with a confidence threshold falling back to a default reaction. The post frames this as a way to show users how an agent interpreted a task and says LangChain uses similar patterns in its internal agents.
LangChain Blog · 🔥 0 - Engineer's AI pipeline over 400 years of archives finds forgotten meteorite, lost rhinos
A software engineer, inspired by historian Benjamin Breen's use of Claude Opus 5.5 to find a new dodo eyewitness account, built an AI research pipeline with Claude Code: a cheap "System One" decision model, Jev, first filters huge volumes of passages (reading 59,000 elephant mentions cost about $3), Claude Haiku then reads, translates and extracts dates and places, and a Claude Code agent checks transcriptions against scans of the original manuscripts. The run processed GLOBALISE's 4.35 million transcribed pages of Dutch East India Company records in a single 12-hour overnight pass. The author reports finding an 1812 reprint in the Java Government Gazette of a Bombay letter describing a meteorite fall near Pandharpur, which if confirmed would be the earliest recorded fall in Maharashtra by 26 years, plus archival details of Javan rhinoceroses sent as gifts to the King of Kandy dying en route in 1738–1740.
Hacker News · AI（100+ 分） · 🔥 0 - Jev founder Diogo Almeida: the AI world before Jev was 'a tragedy'
TypeSafe founder Diogo Almeida, who previously worked on OpenAI's InstructGPT, told the Latent Space podcast that the AI world before Jev was "a tragedy": strong intelligence engines exist, but the interface for wiring them into real business processes is missing. He describes Jev as a System 1 or "large programmable" model trained with reinforcement learning for calibrated decisions (RLCD), so code can directly consume its choices, scores and probabilities and set thresholds for when to act or hand off to a human. He also criticises RLHF mode dropping for distorting calibration, argues specific value judgments should not be baked into a general model's底层 behaviour, and says he dislikes optimising for public leaderboards, adding that benchmark-use restrictions came from preview terms and will be revised.
InfoQ 中文 AI&大模型 · 🔥 0 - OpenAI says Jev inspired its Decisions API, built in about a week
In a Latent Space podcast interview, OpenAI's computer-use product and engineering lead Ari Weinstein and API product lead Nikunj Handa discussed the DevDay (Sept 29) launches: Dot, GPT-6.1 Sol, computer use in the Agents API, and the Decisions API. Handa said the Decisions API was inspired by Jev and was not originally planned; the team had a working prototype in about a week, without retraining a model — reusing Luna weights, constraining outputs to structured results and optimizing first-decision latency for fast classification tasks such as support-ticket triage, and pairing with GPT Live. Weinstein said the biggest improvement in computer use over the past year is that agents now debug and retry better, and can act via page structure, accessibility data and Playwright or by writing code rather than only clicking through screenshots.
36氪 人工智能 · 🔥 0 - GPT-6 Luna leads Decisions model speed ranking
OpenRouter said on X that GPT-6 Luna is currently the fastest Decisions model, at 180ms on global requests. The post ranks Jev and Perplexity Decider behind it. No measurement methodology or latency figures for the runners-up were provided.
OpenRouter (X) · 🔥 0 - Jev: TypeSafe AI's probability-only model, explained
TypeSafe AI emerged from stealth on September 15 with Jev, a model that does not produce free-form text but instead returns estimated probabilities over a fixed answer set — yes/no, multiple choice, or a rating. It went viral: the announcement drew nearly 40 million views on Twitter, over 100,000 people joined its Discord within a week, some 2,000 GitHub projects adopted it, and signups opened on September 20 were paused two days later amid overwhelming demand. Because it is faster and cheaper and its output slots directly into code patterns like if statements, Jev has spawned similar models from the likes of Cloudflare, Amazon and OpenAI.
Understanding AI · 🔥 0 - Ten days with Today AI: a Chinese personal AI assistant that remembers you
A GeekPark writer spent ten days with Today AI, the personal assistant from Teambition founder Qi Junyuan; its China version launched on Sept 24 and connects to Feishu, DingTalk, Tencent Docs and email, keeping briefings, tasks, memory and linked apps inside a single conversation while proactively sending morning/evening digests and story ideas. The reviewer praised its fast, high-density replies, cross-topic memory and daily self-written diaries, but found it misjudges weight: a game mod was localized in 15 minutes, yet the assistant gave a string of useless instructions about where to place the files, leaving the author an hour of trial and error, and it once turned a 60-minute football-coaching script into a nearly hour-long web page build. The piece uses this to frame three hurdles for Personal AI — judgement, ecosystem and trust — noting reports that Meta's Muse leaked roughly 190,000 user conversation records.
虎嗅 AI · 🔥 0 - AI's simmering question: where is all the automation?
A The Information column frames the industry debate over why automation has not arrived even as OpenAI said its unreleased model solved or made major progress on hundreds of significant math and computer science problems. Cognition founder Scott Wu argued that ever-more-capable agents plus more data centers, memory and sandboxes will yield "virtual employees," while ex-OpenAI researcher Diogo Almeida, now at TypeSafe AI, maker of Jev, said today's LLMs are optimized for assistance and fail at unattended automation. Anthropic's Claude Code product lead Cat Wu conceded much automation stalls at a semi-automated stage where Claude does 80% and a human does 20%.
The Information · 🔥 0 - OpenAI launches Decisions API for fast choices, targeting Jev
At DevDay, OpenAI announced a Decisions API that narrows open-ended generation to picking from predefined options and returns a choice plus confidence that code can consume directly, which The Decoder says runs about ten times faster than the Responses API. It currently supports only GPT-6 Luna, at $0.10 per million input tokens with free output tokens in public beta, according to The Decoder, while InfoQ describes it as a limited preview with pricing and customization details to come at general availability. OpenAI also cut its paid API tiers from five to three: Build, Launch and Grow.
The Decoder · 🔥 0 - llm-openai-decisions 0.1a0 plugin wraps OpenAI's Jev-style Decisions API
Simon Willison released llm-openai-decisions 0.1a0, an LLM plugin for OpenAI's new Decisions API announced at last week's DevDay; he had GPT-6 Astra read the new API docs and modeled the plugin on his existing llm-typesafe plugin for Jev. The new decision model, gpt-6-luna, accepts image input as well as text. According to the post, both models charge for input only and not output — OpenAI at 10 cents per million input tokens versus Jev's 4.2 cents — and both support yes/no, choice and score question types.
Simon Willison's Weblog · 🔥 0 - Replit adds GPT-6.1 Sol and Claude Sonnet 5.5, plus Jev agent integration
Replit's changelog lists last week's shipments: the platform now lets users build with the new GPT-6.1 Sol and Claude Sonnet 5.5 models, and lets agents call Jev through an AI integration. It also updated the Settings UI and added enterprise Workplace controls for company-wide rules or controlled exceptions. No details were given on model capabilities, pricing or availability limits.
Replit · 🔥 0 - TypeSafe AI’s Jev turns frequent AI tasks into fast decisions
TypeSafe AI’s Jev is a decision model designed to return structured choices, scores, or calibrated yes/no probabilities instead of conversational text. The model launched on September 15 and drew developer attention for reported low latency and pricing, while TypeSafe AI claims of large speed and cost gains have not been independently verified.
创业邦 科技 · 🔥 0 - TypeSafe AI’s Jev sparks interest in non-generative decision models
TypeSafe AI’s Jev is a decision model that maps inputs to predefined outputs such as yes/no answers, scores, or list selections instead of generating free-form text. CEO Diogo Almeida claims the model is used by about 25% of Fortune 500 companies and processed one trillion tokens per day roughly a week before the report, while separate reports say the startup is discussing a new funding round; these claims were not independently verified in the source.
IT之家 AI · 🔥 0
Experience and discussion from the community
Share my JEV experienceAsk about JEV
Nobody has shared their experience with JEV yet.