Dagens Vibes — 4. september 2026

BREAKING: OpenAI just dropped GPT-6 ASTRA!!! 🚀✨ We’ve been testing it extensively at @every across coding, writing, and knowledge work. My take: it’s a big upgrade from 5.6-Sol, with some frustrating habits that keep it from matching Fable at the top end. Here’s your vibe check: - The best writing model I’ve tried. It’s fast, produces very little slop, and is easy to steer. It’s a good companion for actually working through the writing I do every day. (Not to mention, it one-shotted the first draft of its own vibe check today!) - The computer use is wild. It can go for hours at a time using complicated apps to get work done. It did the first cut of our Fable 5.1 vibe check video...kind of mindblowing - Impressive 3D games and visualizations. It can make beautiful 3D worlds from a single prompt. I one-shotted a historically accurate rendition of the Battle of Waterloo - It can overcomplicate things. (Especially at higher effort levels.) Ask for a simple interface and you get extra labels, buttons, and features everywhere. It has a habit of turning everything into a landing page. It just doesnt quite match Fable's ability to intuitively understand your prompt and do something delightful (without overcomplicating.) Net Result: If you already live in ChatGPT for Work or Codex and can afford it, it’s an easy upgrade from 5.6-Sol. The biggest proof of Astra's effectiveness at helping you do work is our vibe check. We found out it was launching at 3 AM this morning, and had a 4,000 word vibe check + video done by 2 PM. Not possible without this model. I’m reaching for Astra all day, but Fable 5.1 still gets my biggest tasks. On ambitious builds, Fable is better at understanding what I want and taking it further than I would have thought to ask. State of Play: Astra is launching to Enterprise customers today, and the rest of ChatGPT users over the coming days. Now, both OpenAI and Anthropic have a higher class of models that cost more to use. That changes who gets to use frontier AI and how. It's also a new vector of competition between them: Fable and Astra are priced at the same level. We'll see what that means for adoption in the coming days and weeks. read our full vibe check @every today: https://t.co/8BkL5w5DcL

https://x.com/danshipper/status/2095593705214300394

I found a workflow that can save you hours managing GitHub issues and pull requests I ran it in Synara and gave Claude Fable 5.1 eight issues from my repo I used a normal thread as orchestrator of other threads I asked it to: → Create one thread + isolated worktree for every issue → Run Fable 5.1 in high effort inside each one → Keep every agent focused on a single fix → Open a pull request when the work is done → Review the existing PR instead of duplicating the work → Wait for every thread and return the safest merge order Instead of creating and checking eight different chats, I described the backlog once and let the main thread manage the agents This workflow really saved me multiple times, and I'm happy that @trySynara can do this too now!

https://x.com/emanueledpt/status/2095481942875779137

You should start taking prompt caching very seriously 👇 We’re using more AI than ever, and we’re getting increasingly careless with context We open a chat and throw everything at it, web searches, full articles, entire codebases, long conversation histories We already have ways to keep the context window under control, subagents, skills with progressive disclosure, compaction. They all help preserve accuracy while avoiding unnecessary token consumption The next frontier is the cache! Processing input tokens from cache is dramatically cheaper than processing them from scratch, and as a conversation grows, more context gets sent again on every turn because the model remembers nothing between API calls Prompt caching lets the model reuse the same prefix, resume from its cached KV state, and process ONLY WHAT’S NEW Same response, less computation, lower latency, much lower cost But there’s a catch... the cache expires In Claude Code, the TTL depends on how you’re running it: - Subscription, main conversation: 1 hour by default - API key or cloud provider: 5 minutes - Subagents, workflows, and compaction: 5 minutes And here’s an important detail: the TTL clock starts when the request begins, not when the model finishes responding If Claude takes 4 minutes to answer on a 5-minute TTL, you may have 1 minute left before the next turn TYPE FAST! So what does this mean in practice? Should we ask for shorter responses? Break large tasks into smaller steps? Structure agent workflows around cache boundaries? There’s another easy way to lose a cache hit, switching models mid conversation The previous KV state isn’t necessarily deleted, but the new model can’t reuse it, one model’s cache isn’t reusable by another. And this gets even more interesting with Fable 5.1, cache reads dropped to 0.025x - 0.25/MTok, 75% cheaper Managing prompt caching across long running agent sessions is going to become an art Or maybe an entire engineering discipline 👀

https://x.com/dani_avila7/status/2095568897596362866