Heads up - there is a bug where subagents can switch models when the coordinator sends messages to them. I’ve been telling the coordinator to work around this: github.com/anthropics/c... I’m… not impressed with the code quality of claude code tbh.
Who's Who of AI
h.olysh.it
Why they matter
Tracked through public AI activity and peer connections inside the directory.
- AI signals
- 0 past 30d
- Sources
- 0 distinct domains
- Discussões
- 10 past 30d
- Latest signal
- —
Semi-retired technologist. Did k8s, GCE, gtalk and IE. Figuring shit out. Protect Trans kids 🏳️⚧️. Seattle. Signal: jbeda.99 he/him
What they're sharing
Subagent model override silently dropped after a continuation boundary (SendMessage follow-up / post-compaction resume) · Issue #68147 · anthropics/claude-code github.com
Modelith - Domain Model Tooling | Modelith modelith.sh
The new 20% time, minus the time joe.dev
View on Bluesky →
An always-on home for Claude Code joe.dev
The animatronic rubber duck joe.dev
Articles & links
Funny enough, doing a CRM lite was one of the first things @cmcluck.bsky.social did when he started playing with modelith.sh. It was surprisingly good and scoping out the moving parts at that level. Don’t think he actually built anything though.
h.olysh.it reposted
joe.dev/posts/new-20... Love this from @h.olysh.it - this is the conversation about ai I’m having now with upper level engineers. Not the technical impacts but what are the cultural impacts. Who benefits is a big question in that.
I moved Claude Code onto a spare NUC so closing my laptop doesn't kill a running session. 2 interesting things: - I was able to set up a seamless config that includes things like pasting images - This stuff is so *easy* when you are working with an AI agent. joe.dev/posts/alwa…
Rubber duck debugging is when you just talk about your problems and the process of verbalizing them helps you solve them. One of the best ways to use AI, IMO, is as an "animatronic rubber duck". It can really help you sharpen your thinking. Blog post: joe.dev/posts/animat...
Their own posts
Recent commentary
AI can make stupid people feel smart. None of are immune. That includes you. (Stupid people = stupid in a domain. People are multi-dimensional and IQ is bullshit.)
The more I work with LLMs and agents, the more I'm gobsmacked by the n^2 nature of how conversations are handled. For every turn of the conversation, you send the entire previous conversation. This means the costs compound the longer the conversation goes on.
Sleeper Agents but for AI. (This is a real concern for foreign open weight models.)
Their network
In h.olysh.it's orbit
Center = h.olysh.it. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.
Are you h.olysh.it? Show it.
Add the Who’s Who of AI badge to your site or bio. It links back to this profile.
Markdown: [](https://aiweekly.co/whos-who/person/h-olysh-it)