Peter Schuller

Apparently I need to adjust my skills or claude code will refuse to write sub agent reports to files even when explicitly told to.

Well, this is highly unscientific but better than "I used it for a while", and definitely not benchmaxxed: snippets.scode.org/s/rust-co… Quality variance is basically noise at this sample size but still consistent with same ballpark performance - and way faster than both Luna and Haiku.

codex and claude code are so yesterday, let me introduce you to Palantír

lol Google. I was actually considering upgrading to Ultra to try Argon, but your broken end to end user experience prevents me from giving you money.

Much better way to get your Dot to run agents on your devbox - make an MCP server: snippets.scode.org/s/devbox-… Prototype implementation if you want to try/crib it: github.com/scode/devbox-mcp

Been daily driving my agent orchestrator (farhelm.io/) for several weeks and I now feel its ready for others to use. If you try it and have feedback, or even don't and have feedback on presentation, feel free to reply to me or use the in-app feedback flow.

Truly gone full circle. The AI asking me for permission to solve CAPTCHAs to get stuff done. Truly just proof of work at this point with the side effect of annoying humans.

I'll add a datapoint to the model performance story. This is 200 code reviews, 4 reviews per model per commit being reviewed, spread over 10 commits in a few different repos. Link has results plus details (enough to repro etc). snippets.scode.org/s/code-re…

6.1 sol already - didn't expect this. Let's hope this bring it to 5.6-sol level performance or above while keeping the new pricing :)

@LACitySAN Please consider making sure AI agents can easily access your website so that people can easily get information from official sources. As a governmental agency this should be aligned with your goals - make it as easy as possible for citizens to consume the information.