Was issue with upgrade running out of disk space fixed?

The article describes a case that is a perfect candidate to be automated by LM. You don’t have to have real-world knowledge for that.

Would be interesting to see what involves contributing a real thing that’s not found on the net - a fence, footpath, etc. Or contributing a bus stop.

No. If you're making maps and building a database of facts, I think the possibility of hallucinations is actively harmful.

Does the harness apply when you sue Claude model in third party IDE? like Opencode, or third party adds their harness on top, not replacing it?

Claude models seem to work far better in Anthropic harnesses. I don't know if this is because they are trained in that context or because they offer different models through external APIs.

Depends what you mean by "apply." The harness-specific instructions (Claude Code's own system prompt quirks) only get sent if Claude Code is the program calling the API. OpenCode or any other third-party tool writes and sends its own system prompt instead, so those exact lines aren't there. Whatever behavior shows up across different harnesses anyway is more likely a trained default of the model itself, not something coming from a particular harness's prompt.

It’s like Nathan Macintosh joke about AI https://youtu.be/ce-aWzOUs2A?si=9CkJ9x2rRMBdzCyO

The thing he talks about in there - an ad telling a dad to use AI for his daughter’s wedding speech. I agree is just so sad. And I’ve seen LOADS of other ads like that encouraging people to use AI for things like asking someone to move seats on a train, or for a neighbour that plays music loudly. They literally want to drain people of their social skills, and humanity. It’s weird

Trust me, only people who were unable to do it in the first place will substitute basic human skills with AI output. They never developed it in the first place.

Must-see Nathan Macintosh standup about AI https://youtu.be/ce-aWzOUs2A?si=9CkJ9x2rRMBdzCyO

Down with the tech from him is also fantastic!

So Fable can act by itself as audio to midi decoder now? No need for specialised models, it just listens like a person and plays it?

I haven't tried that, but when doing some quick discussion on the topic, Fable pointed me to some other models which do it better.

My task to fable was to take the MIDI and encode it into some proprietary mp3 format. It's still "binary" MIDI encoded in the mp3, it's not simulating the piano and generating waveforms... yet.

LM still can not see and understand the desktop app UI on a level that is acceptable for testing. All the advances in coding are from web dev and thanks to the nature of html UIs. Try to develop a desktop app and it’s like working with a legally blind person who can see some part of the screen is they squint in a certain way but surely will miss all minor details.

This is totally absurd because people don’t buy phone based on car integration they have. They buy car integration that works with their phone. And numbers reflect iPhone vs Android market share.

Such board already exist as you described, and at that URL

So Down Detector is a kind of quantum observation experiment, observing influences the result.

observing is the result