Dagens Vibes — 4. juli 2026

Thariq@trq212

I’ve found the most important part of working with Fable is discovering my own unknowns so I can prompt it better, heres how I do that.

Citeret tweet

Thariq@trq212

https://t.co/hPiZr1kG7r

Simon Willison@simonw

The most interesting Fable tip I've heard so far is to let the model use its own judgement as much as possible I told it "For all coding tasks use your judgement to decide an appropriate lower power model and run that in a subagent" and it seems to be saving a lot of tokens

Peter Yang@petergyang

The AI super app era is here 1. Anthropic and OpenAI want to transform all knowledge work. Both labs want to remake how white-collar work gets done with agents. What started with coding has expanded to design, finance, legal, science, and more. Knowledge workers are now adopting Codex three times faster than developers. 2. The race to build the best AI super app is on. Whoever wins will pull massive attention away from pre-AI knowledge-work tools. The main players are Codex, Claude, Cursor, and a few others. With browser and computer use, I can already get Codex to handle almost everything I want to do on my computer. 3. OpenAI is well positioned for the super app race. ChatGPT has 800M+ weekly active users, and Codex is arguably the best AI super app right now. OpenAI has a clear opportunity to merge ChatGPT and Codex into one app and push agents into the mainstream. 4. Anthropic leads enterprise, but its product suite feels fragmented. Long term, I don’t think it makes sense for Claude, Cowork, Claude Code, and Claude Design to exist as separate products. Working with Claude needs to feel more like working with a single capable coworker, imo. I’m excited about the potential of Claude Tag for team productivity. 📌 More in my recent essay: https://t.co/jj568Tx1NU

Citeret tweet

Peter Yang@petergyang

Here's my new post with 18 hot takes on where AI is headed next: 1. The frontier-only AI stack is collapsing Companies will use a portfolio of models to save costs, with everyday tasks defaulting to low-cost open models from China. 2. The AI super app era is here Codex, Claude, Cursor, and others are competing to disrupt all knowledge work by using agents for everything you can do on a computer. 3. Traditional software risks becoming a dumb pipe for agents Agents will become the default user. They’ll use APIs and browsers to access your website and app without humans ever seeing them. 4. Cloud agents and collaboration are the next wave The future is agents living in the cloud, accessible from any device, and collaborating closely with both you and your team. This will happen very soon. 📌 Read all 18 takes now for free: https://t.co/jj568Tx1NU

leo 🐾@synthwavedd

🚨 SCOOP: As previously reported, OpenAI plan to launch GPT-5.6 once back in office next week, with a target window of July 7-9, but want it out as early as possible within that window (so July 7th is the most likely date). This is also perfect timing to catch customers coming from Claude who have just lost their access to Fable 5 in plans, and I'm told the 5.6 plan limits will be significantly more generous. More aggressive safeguards are already being rolled out in preparation for the launch too, although they probably won't be as aggressive as Fable's. DeepMind have also tentatively set a new launch date for Gemini 3.5 Pro of July 17th. Apparently, this extra time has been spent on a new pretrain (they were planning to keep using the ancient 2.5 Pro base, lol), but it remains to be seen whether it's any good. I'm not hopeful. In other news, work is well underway on a new Nano Banana Pro model based on the new 3.5 Pro base, which I expect to be better received and compete well with GPT-Image 1.

Albert Jiang@AlbertQJiang

https://t.co/mWNOMLuWtN Leanstral 1.5 is here. SoTA on FATE-H/X, 587 on PutnamBench, saturating miniF2F, all with an Apache-2 6B active params model. We are having fun verifying code properties and catching bugs in Rust repos! Tech report covering training environment and evaluations: https://t.co/4zVUZfArn3 We also open-source LeanstralSafeVerify and FLTEval.

Teknium 🪽@Teknium

New optional skill available in Hermes Agent. Unbroker teaches Hermes Agent how to find your personal info on data brokers platforms and get it taken down. Learn more:

Citeret tweet

𒐪@SHL0MS

i'm open sourcing UNBROKER: a tool that finds where your personal info is exposed by data brokers and files the removals for you it runs as a skill in Hermes Agent _________ your data is everywhere; hundreds of brokers publish your name, current and old addresses, phone, email, birthday, even your relatives. anyone can find where you live in about ten seconds CCPA, CPRA, GDPR, and a growing number of state laws say a broker has to delete your data if you ask. there's just no easy bulk button. every broker has a different process and many make it intentionally difficult to exercise your right to delete this is the entire business model for companies like DeleteMe, Incogni, EasyOptOuts; they charge you monthly (DeleteMe is $330/yr for a Family plan) to file removals that you can submit yourself for free, and then you're giving a new company the exact data you want to erase so i built one you just run for free. your data never even has to leave your machine if you run a local model _________ how it works: first it builds search vectors from everything: every name, alias, email, phone, and address you've had (brokers might index you under a maiden name or a house you left in 2014, so the naive "current name + current city" approach can miss profiles). then it fans out parallel sub-agents across the broker list, which refreshes from a maintained public source automation is tiered. when it can handle a broker end to end with your settings, it drives a browser through the opt-out form, sends the email, and opens the confirmation link itself. soft CAPTCHAs clear on their own with a real browser. anything only a human can finish comes back to you as a short list at the end the email side doesn't need a stored password and can send opt-outs and open verification links through your own logged-in webmail. you can also wire up SMTP, or keep it manual and just send the drafts it writes it tailors every request to your jurisdiction, filing under the framework that applies where you live: CCPA and CPRA in California, GDPR in the EU and UK, a general right-to-delete request everywhere else. if you're in California it also uses the state's DROP portal, a single request that covers 500+ registered brokers at once it holds as little of your data as it can, and keeps it local. dossiers are encrypted at rest if you want, opaque ids keep your real name out of every filename and log, and nothing leaves your machine unless you opt in brokers sometimes relist you eventually or new ones find your data, so every case is tracked in a ledger and can be re-scanned on a cron schedule so if your data pops back up it files the removal again https://t.co/2jfQxBYZkW

Devon Govett@devongovett

Why you should use React Aria: • It has 50+ components, including complex ones like data tables, trees, date pickers, color pickers, and tons more. No need to combine multiple libraries to build your app. • It has complex interactions like accessible drag and drop, keyboard multi select, form validation, virtualization, and table column resizing built in. • It is optimized to feel great on touch screens. No weird sticky hover states, conflicts with text selection, etc. • It’s battle tested for accessibility across devices including mobile, going far beyond the ARIA Practices guide. • It has internationalization built in, including localized strings, support for many calendar and numbering systems, etc. • It has a compositional API. Combine components together to create custom patterns. • You get full control. The components are already pretty flexible but if you need even more you can drop down to the hook layer and customize everything. • Great documentation including interactive examples, guides, agent skills, etc. I’m biased but nothing else comes close to this level of functionality, quality, and customizability in one package.

Zane Chee@injaneity

people of pi, pi-computer-use v0.4.0 is here! bringing major overhauls to our computer use architecture, that make it faster, more token efficient and more robust: - context now relies on snapshots rather than attempting to reconstruct the state every time - elements are now progressively disclosed to the agent via searchable folded outlines, instead of lossy ranking - improved input delivery, execution feedback & helper-side preflights to reduce hidden failures in edge cases we've also revamped the permission system to address issues where attribution goes to the wrong application, and patched up some gaps in the CI workflow feel free to push it to the limit here: https://t.co/fix2LOe2h2

Andreas Klinger 🦾@andreasklinger

We think Europe needs more pro-European, pro-tech, pro-abundance, pro-optimism propaganda. So we made it. Posters, t-shirts, hoodies. Full-on propaganda. We've been handing them out at robotics meetups and clubs all over Europe for weeks, and people love them. Why we are doing this: Europeans know more about the companies in the States than the ones right here at home. We need to change that. Time for propaganda. Every poster features a real European company: 🦾 Allonic is braiding humanoids. A completely new approach to building robotic parts. If it works, a number one company worldwide, right here in Europe. 🚜 Voltrac, the electric autonomous tractor (we made a whole video about them). 🏗️ Automated Architecture (AUAR), doing micro-factories for wooden houses.  🪨 Gondor Industries, a stone mason company using robotics. And many, many more to come. This is the first of many drops. More launching in the next few weeks, including flags, EU posters and more. 👉 Get yours at https://t.co/aIZd3n8iVk For Europe 🇪🇺🔥 PS: If you're organizing a robotics event or meetup, have a student club or hacker space, comment or message us and we'll send you a swag box.