one more thing before you automate a loop: learn the work first. you build a better loop when you understand what it's replacing. mattpocockuk's teach skill is good for that: npx skills add mattpocock/skills --skill teach then paste this: /teach me how to run claude code as a durable loop, not a one-shot chat. i keep asking for a change, taking the diff, closing the session. i want the loop skills: when to persist a session, what goes in CLAUDE.md vs .claude/rules vs a skill, when to reach for /goal or routines, and how to verify before calling anything done. it asks about your codebase first, then writes a MISSION.md and a curriculum, and teaches against your real project.

I can't wait for the EU to read the AI news in September!

HTML is so back. Drag and vercel.com/drop

The takeaway from Fable 5 being BANNED by the government: GET GOOD AT LOCAL MODELS SO YOU HAVE 100% CONTROL. My entire weekend was going to be building my craziest ideas with Fable 5. That's now cancelled. So instead of building with Fable this weekend, I've decided I'll go deep on local models: 1. Start with the runtime. Download Ollama or LM Studio first. This is the thing that actually runs models on your machine. 2. Match the model to your hardware. A model's size is measured in billions of parameters (7B, 32B, 70B). Bigger is smarter but needs more memory. Rule of thumb: a 7B model runs on almost any laptop, a 32B needs a good Mac with 32GB RAM, a 70B needs serious hardware like a DGX Spark or a maxed-out Mac Studio. 3. Know which model for which job. Qwen 3 is the best all-around choice for most tasks. DeepSeek for reasoning and coding. Gemma 4 when you need something tiny that runs on a phone. Llama when you want the biggest community and the most fine-tunes. 4. Quantization. You can shrink a model to run on weaker hardware with barely any quality loss. Look for versions labeled Q4 or Q5. This is how a model that "needs" a server runs on your laptop. Learning this one concept changes everything. 5. Connect it to your agent. Point Hermes or your agent stack at a local model. 6. Context window is your real constraint locally. Cloud models give you huge context for free. Local models make you pay for it in memory. A bigger context window eats RAM fast. Keep your sessions tight and your prompts lean or your machine chokes. 7. Learn to give local models tools. A smaller local model with web search, file access, and code execution beats a giant model with none. The capability gap closes fast when you wire up the right tools. The model is the engine but the tools are the wheels. 8. Fine-tuning is more accessible than you think. You don't need this on day one, but know it exists. You can take an open model and train it on your own data so it gets good at your specific domain. I'll probably do a breakdown at some point on this @startupideaspod if people are into it. The lesson from this ban is basically don't build your entire workflow on something that can disappear with a single letter. Own part of your stack. Local models are insurance. It reminds me when people realized they don't own social media accounts. And then you saw people build email lists etc. I remember running a startup and my biggest traffic source was organic FB. All of a sudden, algo changed, and I lost 99% of my traffic. Same sorta moment (but bigger) for AI. This is a wake up call.

Well this is massive: - Every non-US company sees how they can be cut off from US vendors with a snap of a finger. Non-US vendors getting free advertisement - What does this mean for US AI labs’ offices and employees outside the US? Reads pretty draconian What a mess

As a result of a US government directive, we are suspending access to Claude Fable 5 for all users. You can continue to use all other Claude models. Here’s what this means for you: Across Claude products, new sessions will run on your selected default model or Opus 4.8, and existing Fable 5 sessions will end with an error. On the Claude Platform, requests to Fable 5 will also return an error. Please update your integrations to other Claude models. We know this is a disruption to your workflows; we appreciate your patience and support.

Google releases DiffusionGemma.✨ The new 26B-A4B diffusion text model runs locally on 18GB RAM. It supports high-speed text generation, thinking, image, video and 256K context. Run and train via Unsloth Studio. GGUF: huggingface.co/unsloth/diffu… Guide: unsloth.ai/docs/models/diffu…

Hermes Agent now has Automation Blueprints, turning cron jobs into clickable, fillable, conversational workflows.

this is interesting what i fully keep in my head is all the types and services in my application i also know most of the services functions they expose but i no longer really know how `integration.oauth.refresh()` is implemented

on "caring about work" in the agentic era software engineers for the longest of times cared deeply about the code being written, practices being followed. We would fight over tabs/spaces or how imports should be styled. now that frontier models can write all our code to a more than reasonable extent, I think our roles evolve in the same way that we don't everyday worry about the machine level code being shipped. I think of this as "intent": if presented with a problem where every nano-second counts you will spend time going over the gnarly details of the code, if you worry about horizontal scale you will worry about resilience and startup time of your service. my conclusion is that people who "care" will use agents to show that care, it will not readily reflect in the code quality or LOC but when the end user uses it, the care and attention to detail will come through. I for one am very very excited about a world where people can choose to care about the work they are doing to the deepest extent and get joy from it, for some it might still be writing the perfect code but for others it will be doing the impossible...

We heard you wanted to use Codex rate limit resets on your own time. Starting today, we’re rolling out the ability to save rate limit resets to use later. We’re starting Go, Plus, Pro, and Business users with one free reset:

Fable 5 is doing something wild on our FrogsGame post-training task. It trains a weaker model to solve the puzzle, peaks at 68%, and produces the only ~10x improvement we see across the benchmark. It spent 17 hours, 25M tokens without human in sight. 34% pass@1, while every other frontier model averages under 4%. We will publish a more detailed analysis soon.

can we announce the same feature twice? yes re-introducing Raycast Focus

🪟

Hey @Remotion crew, Jarred needs to get really crafty ahead of this big major rewrite release - what if you could drop your fanciest bytes to the aid?

The Grok Build Plugin Marketplace is now in beta. Build with MongoDB, Vercel, Sentry, Cloudflare, and Chrome DevTools plugins from your terminal. Read more x.ai/news/grok-plugin-market…

We're integrating Deep Research as a native skill inside Computer. It now connects to the agent harness that powers Computer, with access to search as code generation, long running sandboxes, connectors, tools, and licensed data. Available now to Pro and Max subscribers.

Some thoughts of mine that nobody asked for on the EU's fight with Apple and my worries related to Mythos and Fable. lucumr.pocoo.org/2026/6/10/g…

Just let Claude Fable 5 rawdog your CAD software One @adamdotnew prompt and it designs an entire Boeing 747 in Autodesk Fusion