@thsottiaux@AnthonyBerlin Same here 019e8a81-07ff-77a0-9c68-e284808fba21
There was a loop between trying to compact the context in goal mode and getting that error.
🤖 The RevenueCat AI Toolkit is here.
It brings RevenueCat into the AI coding tools where app work already happens, so your agent can help set up subscriptions, integrate the Purchases SDK, build paywalls and check metrics.
With Tesla FSD progress in Europe, we’ll see which countries are the most forward thinking, which have the most bureaucracy and which put politics over people’s safety.
Kudos to Lithuania 🇱🇹
SpaceXAI will provide @AnthropicAI with access to Colossus 1, one of the world’s largest and fastest-deployed AI supercomputers, to provide additional capacity for Claude → https://t.co/nfDR9S822L
The last month, Anthropic:
- Quietly nerfed their flagship model harness (Claude Code) without telling anyone
- Banned corporate customers of Claude
- Silently changed plans for customers with certain files in their repo
All evidence that closed models are *massive* risks.
In 3 to 6 months AI will write about 90% of all code. In about 12 months (1 year!) AI will write 100% of all code.
That’s coming from Dario Amodei, CEO Anthropic.
So year looking bad for several people and looking good for self-developing AI