Is there a way to hide the question prompt without skipping it while in CC on desktop? I keep having to try to read what's in the background of the modal to answer the question.
In this screenshot it's asking me to determine if I like the 90 day play it is suggesting but never let me read it or discussed it.
I'd like to be able hide the question to actually read the plan then answer.
Cardiologist wins 3rd place at Anthropic's hackathon. Out of 13,000 applications. Built in 7 days by Michał Nedoszytko MD. Coded day and night - in the hospital, in the cloud, while flying from Brussels to San Francisco.
A few years ago, it would have been impossible for a doctor to build this alone in just a couple of days. AI changed that.
The project is called https://t.co/wAliajqjVF. It is an AI agentic care platform for patients. Including reverse AI scribe it is a companion that guides the patient from the moment they leave the doctor's office.
Powered by the massive context window of Opus 4.6, it allows patients to explore their full medical history, connected devices, Evidence Based resources and external data sources — all in one place.
Today, the barrier to entry has vanished; even a practicing physician can build an application from scratch.
Does anyone else intentionally try to give Claude sloppy prompts to see if it can figure out what you want? It’s very good at knowing what you’re trying to say
Let my daughter talk to my openclaw while driving home from voice lessons today.
In about 10 minutes she had split its personality into a “family” of claws with kids, voices, and a family structure that she can talk to and also had it build this “obby” game that was waiting for her when we got home.
So fun to see how her brain worked with it and how natural it was for her.
Version 1.4.0 is now live!
What’s New:
∙improved live GPS experience with faster search and improved hole data
∙you can post images and videos from your camera roll to the community feed easier
∙Bug fixes and performance improvements
The product announcements that act like their product is part of a Claude or OpenAI release but really are just their own independent product are annoying. It's a creative spin, but i hate having to go figure out if it's actually part of Claude or not lol.
Introducing Claude Opus 4.6. Our smartest model got an upgrade.
Opus 4.6 plans more carefully, sustains agentic tasks for longer, operates reliably in massive codebases, and catches its own mistakes.
It’s also our first Opus-class model with 1M token context in beta.