Expert attention map

The Who's Who of AI

What credible people across AI noticed, why it matters, and where the field is converging or disagreeing.

2,364 searchable experts 2,966 tracked across all sources
Build my stream Create my edition
Filter the conversation Who is saying what?

Combine a professional role with a reaction lens. Both must match the same attributed contribution.

Clear all
New Network reaction maps

See how experts are reacting—not just what they shared.

Posts are grouped by conversation and tone. Select a lens to filter the stream; these are never permanent labels on people.

0 live reaction maps in this view

No development in this filter has enough independent reactions yet. The maps appear as soon as the evidence supports them.

Showing signals surfaced by h.olysh.it ×
Most important

The developments commanding sustained expert attention

One card per development. Sources are clustered; reaction bundles describe these posts, never the people behind them.

Established Models & releases Development 19d ago
Claude Code subagent model override bug reported

Subagent model override silently dropped after a continuation boundary (SendMessage follow-up / post-compaction resume) · Issue #68147 · anthropics/claude-code

2 experts are actively discussing the implications.

1 expert 0 communities 1 sources clustered
h.olysh.it

“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.”

2 experts discussed this · 3 posts
Dare Obasanjo: Decided to try Claude Fable this weekend and it burns so many tokens that it’s unusable with the $20 plan. Definitely not worth it unless it gets better at one shotting solutions and following inst…
h.olysh.it: I’ve had great luck having it do design and coordination and aggressively use sonnet subagents for implementation. Have it do code review and fix I a loop 3 times. Still can burn through some token…
h.olysh.it: 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 i…
Open the full discussion →
Primary source github.com ↗
Established AI field signal Signal 8d ago

An always-on home for Claude Code

1 directory member surfaced this signal.

1 expert 0 communities 1 sources clustered
h.olysh.it

“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…”

Primary source joe.dev ↗
Established AI field signal Resource 19d ago
Modelith domain model tooling launch

Modelith - Domain Model Tooling | Modelith

1 directory member surfaced this signal.

1 expert 0 communities 1 sources clustered
h.olysh.it

“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.”

Primary source modelith.sh ↗
Debates gaining attention

What experts are discussing without an anchoring article

4 experts · 20 posts · 12d ago
Phillip Carter austin h.olysh.it apenwarr.ca
Multiple readings Building & implementation · 2 Context & explanation · 1
apenwarr.ca: Alarmed at this trend of people finally realizing MCP is a pointless abstraction, then skipping right over publishing a regular boring API, and instead launching new CLIs for agents to use for some…
apenwarr.ca: I mean, it’s not *really* baffling. It’s Conway’s Law and the people who own the API wouldn’t listen to you and you weren’t allowed to publish a second API after people saw through the MCP trick, b…
Open the thread →