Yet another Hacker News

I stress-tested Meta Muse until its agent control plane started timing out

5 points mpkc 45 minutes ago 4 comments

nzoschke 22 minutes ago | parent

I dont fully understand how these black box agent computers will actually work.

One of the huge value adds of the agent computer paradigm is your agent can also fix and customize its own software.

I’m working on a similar agent computer and having the full source code plus a plugin system is the thing that really made it start working.

Something tells me Meta and Grok bots won’t give you this level of control.

More thoughts at this blog:

https://housecat.com/blog/agent-computer-101

liuliu 4 minutes ago | parent

I sort of understand DSH arch, and their choices, but still baffled by why you would want the agent to change its own agent loop other than the system prompt (in that extension, memory / soul / tools / skills).

arjie 3 minutes ago | parent

It turns out a lot of the value is in the agent being able to stitch together pre-existing tools. I, too, have a personal agent but my friends using Muse or Instinct approach the functionality I use mine for quite easily.

The insight that enables this is a sophisticated coder can build tools an unsophisticated assistant can use. So our hosted model isn’t as smart but executes at 100+ tok/s single stream across 8 streams on our local hardware at frontier level.

But the code Fable provides is much better. The unsophisticated guy can build little tools but self-modification leads to a tower of cards.

bradfa 6 minutes ago | parent

This writing style, which reads like an LLM wrote it, is draining to read.

I put up with it when I'm actively using an LLM tool, because I just accept that this is how these tools write, but when reading a blog I expect to read words written in one of the vast varieties of normal human-written blog formats.