I got messages from concerned devs how their codebase was uploaded without their knowledge or consent via Grok CLI (from SpaceX).
It seems that SpaceX sneakily uploaded this code for lots of users and customers… absolutely unacceptable IMO
Trust burnt like there’s no tomorrow
This is why competition leads to much better outcomes for customers and consumers, in general
If it was not for GPT-5.6 released a few days ago, Anthropic would have most likely removed Fable from most paid plans, and charged $$$ for access
But with GPT-5.6 out, they cannot
lately after a big change instead of reading the diff i ask the agent for a summary of what it did in each file
anything weird sticks out immediately and 1-2 prompts later it's completely as i want it
files + functions signatures i need to know, care less about function body
We showed react-native-bottom-sheet at App.js, and it's ready to use today, built with support from @gobimaps.
The sheet host, gestures, snapping and scrolling all run in native code, so drags stay smooth even when the JS thread is busy.
Let's do a deep dive 🧵
This is exactly why experienced software engineers are valuable and will be valuable.
If you don’t know what good code looks like you will have no idea if what the models generate are any good
Of course “AI reviews the code” etc etc… it doesn’t work as reliably. Via @mitchellh
Coincidentally, 3 out of the last 4 weeks I could not include a link to Spotify when releasing my podcast episode, b/f Spotify was down.
2x an outage in publishing the podcasts, 1x the complete web player down
Have not experienced such poor reliability from Spotify in forever
Agents are particularly hard-to-debug software.
For one, and by design, AI models behave in non-deterministic ways. Even two identical prompts don't always yield the same output.
But agents are also complex distributed systems. They involve multiple steps of computation across functions and sandboxes, touching dozens of API services that can go down, rate limit you, etc.
Nailing down observability out of the box for https://t.co/nDDXqUmOlD on Vercel was a key priority for the team, and the feedback so far has been 🔥↓
I don’t know. I need to learn.
The rise of LLMs is worsening this situation. There seems to be a growing trend where people don't even know what they don't know. It’s actually a crisis.
Upgrading your Expo app has never been smoother.
These days you can hand the whole upgrade to Claude Code or Codex with the expo/skills library. We see a lot of people having success with this.
Obviously every app is a bit different so we also have a full guide to help you work through any complexities:
https://t.co/RgRURadrOO
The postmortem from Coinbase's 10-hour outage is out and... damn
They run global trading from a single region because of latency. OK, I understand.
BUT they have no automated failover prepared!
Are they praying the region never goes down?? Doesn't compute for me...
Things I really dislike about Fable:
1. Anthropic collects my prompt history, stores it, and does whatever they want with it for 30 days. No opt-out
2. They can nerf their most expensive model without telling me, billing me the same amount, wasting my time. Whenever they want
Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use.
Its capabilities exceed those of any model we’ve ever made generally available.