Introducing Griffin, the first model to pass the video Turing test. 48% of people who talked to it live thought it was a real human. Previous systems have had a pass rate <3%. It is #1 on NVIDIA's benchmark for full-duplex AI video. It’s the first Human Interaction Model (HIM).

the 𝚌𝚕𝚎𝚏 models have a few unique properties worth writing home about: ▶ vision encoder: classify images, not just text ▶ trained for 256k context (64k hosted) ▶ clef-flash around 13x faster than Jev ▶ drop-in jev api compatible ▶ open source under apache 2.0 ▶ hosted on workers ai, taking advantage of edge GPUs for latency ▶ fine-tune it on your own data with our new RL platform

¡Acaba de salir Git 2.56! Y trae algo nuevo interesante: $ git branch --delete-merged Para borrar fácil las ramas que ya han sido fusionadas.

Crazy how we're normalizing a $500 AI subscription. That's a whole ass car payment. Wouldn't surprise me to eventually see Pro 1000 plans at some point.

Added the auto fix flag. The output is a little verbose and I need to speed this up but it's looking decent right now. Spent many hours on this. Being able to enforce personal preferences (like how comments are made, how booleans are named, etc) is going to be so nice.

Jev Founder, Diogo Almeida, just released a 12-page PDF on how to use Jev with LLMs It is more useful than most paid AI courses: this is a 10-step blueprint on how to build a faster, cheaper and more controllable AI system around Claude, Codex, Grok or any other LLM: step 1 → split the responsibilities: the LLM generates, Jev makes bounded semantic decisions and deterministic code keeps authority step 2 → build the state: give Jev the current request, relevant evidence, policy and proposed action instead of sending the entire conversation step 3 → choose the right primitive: Choice selects a route, Score evaluates an ordered rubric and Noul returns the probability that a statement is true step 4 → replace giant evaluation prompts with atomic questions: intent, urgency, evidence, risk and scope become separate typed decisions step 5 → put Jev before the LLM: select the context, tools, provider and workflow before paying for an expensive generative call step 6 → give the LLM a bounded job: once Jev selects the route, the model receives only the instructions, files and tools required for that branch step 7 → put Jev after the LLM: check whether the result answers the request, uses sufficient evidence and stays inside the permitted scope step 8 → route by confidence: high-confidence low-risk cases proceed automatically, uncertain cases request more context and consequential actions go to review step 9 → batch independent decisions: ask multiple Choice, Score and Noul questions over one shared state instead of creating another LLM call for every judgment step 10 → record the complete decision receipt: state version, question, probabilities, selected route, model, latency, outcome and human override most AI courses teach you how to write a bigger prompt this 12-page guide teaches you how to build the control system around every prompt the result: smaller contexts, fewer unnecessary LLM calls, safer tool execution and decisions you can actually inspect, test and improve Send this PDF and the original Jev article to Claude Code or Codex and start rebuilding one expensive LLM decision at a time ↓