Lance Martin

speaker

624 appearances 1 recordings 1 series first heard Sep 2025 last heard Sep 2025

Lance Martin’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

No recordings in the last 12 months.Older appearances are listed below; set an alert to hear about the next one.

newest first · ▶ plays the moment

But you still have that raw context available to you.

So you don't have kind of lossy compression or lossy summarization.

So I think that's an important and useful caveat to note on the point of summarization or pruning.

You have to be

That's actually very interesting.

Drew Brunick has a nice blog post that hits this point.

He talks about this theme of context poisoning, and apparently Gemini reports on this in their technical report.

He talked about, for example, a model can perform a hallucination, and that hallucination is stuck in the history of the agent.

And it can kind of poison the context, so to speak, and kind of steer the agent off track.

And I think he cited a very specific example from Gemini 2.5 playing Pokemon, they mentioned in the Tech Report.

So that's one perspective on this issue of we should be very careful about mistakes in context that can poison the context.

That's perspective one.

Perspective two is like you were saying, is if an agent,

If it makes a mistake, for example, calling a tool, you should leave that in so it knows how to correct.

So I think there is an interesting tension there.

I will note it does seem that cloud code will leave failures in.

I notice when I work with it, for example, it'll kind of have an error, the error will get printed, and it'll kind of use that to correct.

And in my experience, as I work with agents in particular, for tool call errors, I actually like to keep them in.

Personally, that's just been my experience.

I don't try to prune them.

Showing 301–320 of 624 · page 16 of 32