Tokens are burning ripping out all the web stuff from farhelm.io/ (replacing with GPUI in preparation for Linux desktop support). It should be interesting - also baking in code improvements prioritized based on analysis of the past few months of bug fixes due to agents not applying reasonable good practices. Woke up to screenshots of an early milestone this morning: snippets.scode.org/s/farhelm…
1
1
118
s/fire/allow/ and this is me yelling at macOS to stop getting in the way of my agents with privacy/accessibility protections in VMs...
1
1
86
The most ridiculous "safeguard" block I have ever seen. Literally just having a design/goal planning session for a major change and just wanted to record a verbatim copy of our planning conversation. Apparently it's triggering a "reasoning_extraction" safeguard.
2
92
This is happening repeatedly nowadays. I'll find that sol is still working on something after many hours. I'll ask an agent to troll the transcripts and tell me if it's going off the rails, and I found that yeah something went off the rails into needless complexity. Then I have to intervene.
I think I'm going to start having an agent monitor transcripts and start automatically nudging instead of waiting for me to wake up in the morning.
1
2
236
WhisperX + AI agent is doing a really good job editing audio voice over for me. It appears this will trivially remove all the tedium of editing away pauses, stumbles and re-takes. I can't believe I didn't set this up before. All on a remote Linux box. The screenshot is of a throw-away web interface using Remotion Studio. Took me less time to set up than it's taken me to edit even a single voice over narration in any one past video.
1
72
Apparently I need to adjust my skills or claude code will refuse to write sub agent reports to files even when explicitly told to.
2
3
450
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.
1/4 Today, we’re releasing Mercury 3. Mercury 3 is by far our most powerful model and the most intelligent diffusion LLM ever released. It outperforms GPT-6 Luna and Haiku 5.5 on quality while running at 1000+ tok/sec.
104











