TypeSafe exits stealth with decision model Jev and RLCD training method

On September 16, TypeSafe ended roughly two years in stealth, releasing Jev, its first System One model, along with a new training method called RLCD. Founder Diogo Almeida (@CompleteSkeptic) says he worked on instruction-following research behind ChatGPT at OpenAI, and many reposts call him a "ChatGPT co-inventor," though this identity is self-described and unverified. All performance claims are vendor-side, with no independent evaluations yet, and some skepticism has already surfaced.

Confirmed

• TypeSafe released the model Jev and the training method RLCD; per @rohanpaulai, Jev is the company's first System One model, and multiple reposts describe Almeida as an InstructGPT paper co-author.
• Jev is not a chat model but "decision intelligence": it takes natural-language questions (including ambiguous or subjective ones) and returns probabilities for yes/no or custom categories via a pure API, with no text generation. A typical use case relayed by @hardimanjames: asking whether a support ticket customer sounds angry, returning a probability like 0.9 in about 0.7 seconds. @bindureddy characterized Jev as a classifier that makes intelligent decisions among options, arguing such near-free classification is a great complement to agent platforms; she further proposed that small models outputting option probabilities in a single forward pass could act as decision-makers, easing the serial bottleneck (tool selection, branching, retries) in current agent architectures and enabling thousands of parallel steps.
• The division of labor: large models handle hard reasoning while massive small decisions (routing, fraud detection, moderation, verification) go to models like Jev. Technically it skips autoregressive token generation, mapping unstructured state to type-safe probabilistic decisions in parallel. @FrankFelixAI likened this to how Transformers overtook RNNs by replacing serial with parallel computation—fast and cheap, but incapable of generating text. The AI Daily Brief's video offered a similar reading.
• Per @Profanion citing The Register, the vendor claims far lower hallucination rates than traditional LLMs and much cheaper outputs.
• Vendor claims: 20-200x faster, 40-400x cheaper than existing models, free output tokens, sub-500ms responses, no hallucinations. @heyabusiddik relayed input pricing of $0.042 per million tokens; @TheMoonMidas relayed 155x cheaper and 20x faster than Opus; @soumitrashukla9 relayed 25x faster and 600x cheaper than Fable-level judgments—figures vary across reposts, all originating from the vendor.
• The vendor also demoed Jev playing Doom in real time to showcase low-latency decision-making (per @alexcovoeth).

Unconfirmed

• Speed, cost, and "zero hallucination" claims lack systematic independent evaluation or benchmark verification.
• "ChatGPT co-inventor" is self-described; @bennash explicitly flagged it as unverified. @mohbibi's repost noted skepticism that Jev is merely a specialized diffusion model, and @karmay007 mentioned the claims were mocked online, with no official response.

Why it matters

• If the claimed latency and cost hold, Jev could dramatically lower the barrier to embedding many judgment calls in automated workflows. @bindureddy's architectural thesis—that decision-makers can free agents from serial bottlenecks—is a hypothesis worth tracking.
• "Structured probabilistic output instead of text generation" represents a product path divergent from mainstream chat models; third-party evaluations, founder identity verification, and technical details merit follow-up.

2026-09-16 ~ 2026-09-18 · 86 related posts

Full story(19 episodes)→

• Episode 1: TypeSafe exits stealth with decision model Jev and RLCD training method(2026-09-16, 86 posts)
• Episode 2: TypeSafe AI launches Jev, a dedicated evaluation model showing major speed and cost gains in tests(2026-09-16, 8 posts)
• Episode 3: Vercel fx to adopt Jev safety reviewer, up to 18x faster(2026-09-17, 3 posts)
• Episode 4: OpenJev Open-Source Clone Runs Jev-Style API on One RTX 3090(2026-09-17, 3 posts)
• Episode 5: TypeSafe AI Launches Jev, a Decision-Only Model That Outputs No Text(2026-09-17, 73 posts)
• Episode 6: Mystery decision model Jev sparks wave of community benchmarks(2026-09-18, 6 posts)
• Episode 7: TypeSafe AI's Jev model and RLCD method spark debate(2026-09-18, 3 posts)
• Episode 8: LangChain Publishes Tutorial on Building an Agent Harness with Jev(2026-09-18, 7 posts)
• Episode 9: Jev Ecosystem Explodes with Wave of Popular GitHub Projects(2026-09-18, 4 posts)
• Episode 10: Jev, the Decision-Only AI Model, Goes Viral for Speed and Cost(2026-09-18, 33 posts)
• Episode 11: TypeSafe Jev Decision Models Spark Debate on Breakthrough, Skepticism and Replication(2026-09-18, 7 posts)
• Episode 12: Jev Matches Classifiers at 100x Lower Cost(2026-09-19, 2 posts)
• Episode 13: Jev Positioned as LLM Router, Not a Replacement(2026-09-19, 2 posts)
• Episode 14: Developers Hail Jev as Top Value Model for Batch Labeling(2026-09-19, 2 posts)
• Episode 15: JevBench Launches: Jev 1.13 Holds Narrow Lead as Open-Source Rivals Close In(2026-09-19, 8 posts)
• Episode 16: TypeSafe AI's Decision Model Jev Explodes in Popularity, Setting Vercel AI Gateway Adoption Record(2026-09-19, 14 posts)
• Episode 17: omarsar0 Tests Jev as a New Primitive: Cheap Verifiers for Long-Running Agents(2026-09-19, 10 posts)
• Episode 18: Dev Tests 16 Models on Calibration: Jev Fast and Honest but Only 10th in Accuracy(2026-09-19, 8 posts)
• Episode 19: Independent Tests Confirm Jev Classifier's Accuracy at Fractional Cost(2026-09-19, 4 posts)

• ChatGPT Co-inventor Unveils Jev, Claims 20x Faster and 40x Cheaper via New RLCD Method — damianplayer · 2026-09-16
• Ex-OpenAI researcher launches TypeSafe's Jev: System One models 100x faster, no hallucination — rohanpaul_ai · 2026-09-16
• TypeSafe launches Jev: a 20-200x faster, 40-400x cheaper model that turns fuzzy questions into probabilities — danshipper · 2026-09-16
• Self-Styled ChatGPT Co-Inventor Launches 'Jev' Model Claiming No Hallucinations, Free Output Tokens — damianplayer · 2026-09-16
• Ex-OpenAI RLHF builder launches Jev: a chatless decision model with 150ms responses and $42/B input tokens — SucceededMind · 2026-09-16
• TypeSafe AI launches Jev, a model for fast structured decisions with confidence scores — yogthinks · 2026-09-16
• ChatGPT co-inventor's startup launches Jev, a decision model claiming ultra-low hallucination — hardimanjames · 2026-09-16
• Typesafe launches frontier model Jev, claims 20-200x speed and 40-400x cost gains — hardimanjames · 2026-09-16
• TypeSafe launches Jev: a structured-probability model that judges agent outputs in 0.7 seconds — hardimanjames · 2026-09-16
• TypeSafe emerges with $40M seed and Jev, a frontier model claiming 100x speed at <100ms latency — hardimanjames · 2026-09-16
• TypeSafe emerges from stealth with $40M seed led by DCVC; first model Jev claims 100x speed — hardimanjames · 2026-09-16
• [source] Jev, a near-free classifier model, launches as a decision engine for agent platforms — bindureddy · 2026-09-16
• [source] TypeSafe AI debuts Jev, a decision-making model with claimed ultra-low hallucination that plays Doom — Profanion · 2026-09-16
• Stealth startup launches Jev, a frontier model that plays Doom in realtime, claiming 20-200x speed and 40-400x cost cuts — alexcovo_eth · 2026-09-16
• Jev, the viral model isn't a chatbot: it outputs probabilities fast and cheap — rkulidzan · 2026-09-16
• TypeSafe AI Launches 'System One Models': Jev, a Typed Decision Engine for Software — bfrench · 2026-09-16
• Ex-OpenAI researcher launches Jev, an automation-first model claiming 200x speed and 100x cheaper — AI寒武纪 · 2026-09-16
• Jev model claims 40-400x cheaper than Gemini; dev backtest finds it faster and more consistent — FrankFelixAI · 2026-09-16
• Jev is a smart classifier, not a frontier LLM — a contrarian analysis — DavideCrapis · 2026-09-16

31 near-duplicate retellings: soumitrashukla9 · lateinteraction · hackgoofer · sedielem · lateinteraction · danshipper · soumitrashukla9 · hardimanjames · soumitrashukla9 · hardimanjames · hackgoofer · hardimanjames · schwentker · aigclink · soumitrashukla9 · SimplyAnnisa · HeyAmit_ · bclavie · hackgoofer · markjeffrey · mohbibi_ · jamesbrooksco · FrankFelixAI · RileyRalmuto · TianbaoX · bennash · karmay007 · sedielem · hey_abusiddik · rohanpaul_ai · hackgoofer