Note: The lecture talks mostly on always-on agents and not necessarily mult-agent system.
pss314 1 hours ago [-]
CMU's 11-768: AI Agents course https://www.cmu-agents.com/ looks really good. I haven't had a chance to go thru it yet.
phainopepla2 4 hours ago [-]
Perhaps I'm being uncharitable, but when I open up a page that was obviously created by Claude, I just close it again.
KellyCriterion 4 hours ago [-]
TBH, this one is an example of the rather good bucket, Id say?
I have seen much much worse examples on corporate blogs for example, where I question if authors even understand how to use any publishing system and how colors & info architecture works :-D
l9o 3 hours ago [-]
haha I agree that the information seems well laid out in this case, but the "Anthropic terracotta" is waaay too overused nowadays
brkomir 2 hours ago [-]
I usually run 4-5 claude sessions in parallel on the same branch, each with its own working plan or work item. They coordinate almost in real time, leaving messages in a shared queue and picking them up every 30 seconds. What keeps them from stepping over each other's work is a commit script that allows only staged changes from one session to be committed at a time.
Where it actually pays off to have separate sessions is the code review. Every code change that affects how the app behaves is checked by a session that didn't write the change. Some numbers: 4,454 verdicts on 4,471 commits since September. About four in five first reviews found something, and about half asked for changes.
cgio 2 minutes ago [-]
They always find something. I am at the level where in a review I allow the reviewer to give me the most important item only and explain its impact.
albertgoeswoof 2 hours ago [-]
What’s an example of a multi agent system that people are using?
empath75 4 hours ago [-]
If you leave "The Honest Summary" in anything Claude wrote, I am not going to read any of it, shows a complete lack of care or interest in what you are doing.
I don't care if you are having Claude write something for you, but I feel like I spent more time writing these two sentences than this person put into this post.
scubbo 3 hours ago [-]
My opinion has shifted over the last few months. Instead of valuing effort put into "putting words together", I am trying to judge the value that I get _from_ the words[0].
I'm reminded of a passage in Stephen Fry's "The Liar"[1], which draws the distinction between a book as an object of art, and a book as a vehicle for communication. If the message is worthwhile, I don't care if it was blurted out by a model or if blind monks inscribed it by hand into vellum parchment.
Don't get me wrong, there's certainly correlation - if I _know_ you've taken a lot of effort to write something, the chances are good that there is worthwhile content being communicated. But the correlation is _not_ perfect.
[0] when it comes to technical writing that intends to communicate information. Narrative writing that intends to evoke an emotion or viewpoint is a different story!
The problem is there's no signal for the recipient that the value being delivered aligns with the intention of the human who set the prompting chain into action, right?
If an AI auto-outputs something with no sign of final check-off by a human, we don't even know if the intention of the human is to spam 100 different articles and delete 99 based on perceived success, or if the AI actually helped them translate something worth saying.
edit: One might argue that value and intention should be kept separate, but clear intention is also an indicator of value, and these days there are dozens of sources of material. It's very easy to "talk" at the void, and very difficult to figure out where to "listen". If an author doesn't try to make "listening" easier, then it puts the value they hold into question if they don't care about it enough themselves.
goosejuice 2 hours ago [-]
Beyond that, criticism based on a simplistic aversion to the mere usage of an LLM can be ablelist. I think few of us want to give our own time to things others didn't invest time in, but how do you really know why the reader used an llm, or even if they did, at a surface level?
There's obviously no obligation to read someone else's shit, but there's no obligation to criticize it without context either. Why not criticize the content instead of the assumed methods?
FLeXMurphy 2 hours ago [-]
I remember all these topics being discussed... well over 25 years ago, though I'm sure they are much older than that.
bob1029 5 hours ago [-]
Sub agents are significantly more useful than multi agents.
Wrap a nested prompt with a tool call that is invoked by the caller prompt. That is the answer to all your suffering. You can repeat this for as many layers of invocation as you desire. You can layer determinism and non-determinism as much as you like in whatever orders you see fit with additional alignment, retry policies, logging, etc.
Agents running concurrently will not go any faster than one well-designed hierarchical agent system.
Imagine the simple task of incrementing a global counter. That would be my #1 benchmark. If you can demonstrate a MAS can increment that counter faster than a single agent can (monotonically without skipping), then I will happily delete 100% of the AI-related code I've authored and start over using your ideas.
vielite1310 2 hours ago [-]
Agree on this. I have been using oh-my-pi and subagents just works for me.
I have never see a case where I need multi-agents talking to each others or something
gbnwl 4 hours ago [-]
What harness are you using? In both Claude Code and Codex I run into the issue of subagents being unable to dispatch their own subagents, so I haven't been able to play with "many layers of invocation".
bob1029 3 hours ago [-]
Custom harness, custom tools.
With custom we don't have to disclose to the caller that the implementation of the tool is another LLM. Each piece of deterministic tool code can firewall the perspective of the model as appropriate.
Think of a sub agent as being isomorphic with a tool call.
dominotw 5 hours ago [-]
depends on what type of problem it is
bob1029 4 hours ago [-]
I am curious if we have any examples of problems that can only be solved via multiple concurrent prompts coordinating in real time.
alala-lala-lon 4 hours ago [-]
[dead]
nzjrs 2 hours ago [-]
Slop
kadharmfn 5 hours ago [-]
[flagged]
RetardedBastard 2 hours ago [-]
[dead]
cush 4 hours ago [-]
Does anyone else open sites with this default claude code theme and immediately close them?
Rendered at 21:20:46 GMT+0000 (Coordinated Universal Time) with Vercel.
Lecture recording: https://www.youtube.com/watch?v=L1OBRtfPS34
Slides: https://drive.google.com/file/d/1b8WiBk_lcB3ue-jZMLijSUMLj6S...
Note: The lecture talks mostly on always-on agents and not necessarily mult-agent system.
I have seen much much worse examples on corporate blogs for example, where I question if authors even understand how to use any publishing system and how colors & info architecture works :-D
Where it actually pays off to have separate sessions is the code review. Every code change that affects how the app behaves is checked by a session that didn't write the change. Some numbers: 4,454 verdicts on 4,471 commits since September. About four in five first reviews found something, and about half asked for changes.
I don't care if you are having Claude write something for you, but I feel like I spent more time writing these two sentences than this person put into this post.
I'm reminded of a passage in Stephen Fry's "The Liar"[1], which draws the distinction between a book as an object of art, and a book as a vehicle for communication. If the message is worthwhile, I don't care if it was blurted out by a model or if blind monks inscribed it by hand into vellum parchment.
Don't get me wrong, there's certainly correlation - if I _know_ you've taken a lot of effort to write something, the chances are good that there is worthwhile content being communicated. But the correlation is _not_ perfect.
[0] when it comes to technical writing that intends to communicate information. Narrative writing that intends to evoke an emotion or viewpoint is a different story!
[1] https://blog.scubbo.org/posts/books-as-vehicles/
If an AI auto-outputs something with no sign of final check-off by a human, we don't even know if the intention of the human is to spam 100 different articles and delete 99 based on perceived success, or if the AI actually helped them translate something worth saying.
edit: One might argue that value and intention should be kept separate, but clear intention is also an indicator of value, and these days there are dozens of sources of material. It's very easy to "talk" at the void, and very difficult to figure out where to "listen". If an author doesn't try to make "listening" easier, then it puts the value they hold into question if they don't care about it enough themselves.
There's obviously no obligation to read someone else's shit, but there's no obligation to criticize it without context either. Why not criticize the content instead of the assumed methods?
Wrap a nested prompt with a tool call that is invoked by the caller prompt. That is the answer to all your suffering. You can repeat this for as many layers of invocation as you desire. You can layer determinism and non-determinism as much as you like in whatever orders you see fit with additional alignment, retry policies, logging, etc.
Agents running concurrently will not go any faster than one well-designed hierarchical agent system.
Imagine the simple task of incrementing a global counter. That would be my #1 benchmark. If you can demonstrate a MAS can increment that counter faster than a single agent can (monotonically without skipping), then I will happily delete 100% of the AI-related code I've authored and start over using your ideas.
I have never see a case where I need multi-agents talking to each others or something
With custom we don't have to disclose to the caller that the implementation of the tool is another LLM. Each piece of deterministic tool code can firewall the perspective of the model as appropriate.
Think of a sub agent as being isomorphic with a tool call.