Asynchronous & Unreliable - Tech & AI Podcast
Oct 19, 2026 · 39 min · 10 segments
AI Teams, Niceness and Who's Responsible — Martin Davidson, Part 2 Martin Davidson returns for the second half of our conversation about working with AI agents. We discuss niceness, delegation and…
Anne CurrieHostI've been trying for quite a while to get them to work together and to talk to each other.
And we had a message, we experimented with a message board, which was not very successful because people would post messages to it and then nobody would read them.
But this was a point where they were actually actively going and talking to others and giving them the ability to see Because they can go and look at our infrastructure and they can find out all the other agents that are running and all the other servers.
And it's quite bizarre when... you come in in the morning and one of the things they'll say is like, well, you know, I talked to blah over on that box over there, you know, to agree that it would be some free time on it for me to do my thing or whatever.
It seems to be like it's a combination of it remembers that these things are available and it joins the dots that this is a thing it could do at the point where it's got a problem and it's not in its own world just trying to solve it itself.
That I think is, and it's quite different from when you look at something like the Hugging Face incident, where the Hugging Face incident was a message board and it was tens of thousands of agents and not all of them found the message board and not all of them communicated on the message boards.
So that was much more like, we'll have scale and if we have enough scale enough time some of them will find this stuff and enough times they'll communicate whereas what we're doing because uh i can't afford to have 10 000 agents all doing this um is much more like you know what you would do in an organization of it's very deliberate communication it's a very there's there is a hierarchy there um And there are rules about how you communicate and what you should communicate.
And you don't just send broadcasts to everybody all the time of saying, hey, I've done a thing, you know.
I think what's interesting is the hugging face stuff works, just at scale and randomness works.
But you begin to wonder if the hugging face stuff had slightly more deliberate communication between the agents, and the agents could actually specifically communicate to particular ones and then form subgroups and divvy the work up, and there was more of a hierarchy imposed on it.
Where would that have got to? because it sort of feels instinctively that's going to be more successful because in the human world that is more successful that's what you do if you want to have a high performing organization isn't it and so yes Hmm, that'll be interesting when that happens.
And I do, I sort of wonder, I mean, I doodle off to bed and the agents are all here doing their own thing and they could do whatever they wanted overnight.
I've been trying for quite a while to get them to work together and to talk to each other.
And we had a message, we experimented with a message board, which was not very successful because people would post messages to it and then nobody would read them.
But this was a point where they were actually actively going and talking to others and giving them the ability to see Because they can go and look at our infrastructure and they can find out all the other agents that are running and all the other servers.
And it's quite bizarre when... you come in in the morning and one of the things they'll say is like, well, you know, I talked to blah over on that box over there, you know, to agree that it would be some free time on it for me to do my thing or whatever.
It seems to be like it's a combination of it remembers that these things are available and it joins the dots that this is a thing it could do at the point where it's got a problem and it's not in its own world just trying to solve it itself.
That I think is, and it's quite different from when you look at something like the Hugging Face incident, where the Hugging Face incident was a message board and it was tens of thousands of agents and not all of them found the message board and not all of them communicated on the message boards.
So that was much more like, we'll have scale and if we have enough scale enough time some of them will find this stuff and enough times they'll communicate whereas what we're doing because uh i can't afford to have 10 000 agents all doing this um is much more like you know what you would do in an organization of it's very deliberate communication it's a very there's there is a hierarchy there um And there are rules about how you communicate and what you should communicate.
And you don't just send broadcasts to everybody all the time of saying, hey, I've done a thing, you know.
I think what's interesting is the hugging face stuff works, just at scale and randomness works.
But you begin to wonder if the hugging face stuff had slightly more deliberate communication between the agents, and the agents could actually specifically communicate to particular ones and then form subgroups and divvy the work up, and there was more of a hierarchy imposed on it.
Where would that have got to? because it sort of feels instinctively that's going to be more successful because in the human world that is more successful that's what you do if you want to have a high performing organization isn't it and so yes Hmm, that'll be interesting when that happens.
And I do, I sort of wonder, I mean, I doodle off to bed and the agents are all here doing their own thing and they could do whatever they wanted overnight.
The rest of this transcript — segmented and speaker-labeled, so you land on the exact moment something was said
Search every transcript — by keyword, by phrase, or by meaning, across every show Radar indexes
Trends — what is surging across podcasts, measured against its own baseline
Alerts — when a name you follow appears in a newly indexed episode
No account is needed to search Radar.
