Is there a half-life for the success rates of AI agents?

Post by libraryofbabel » Wed, Jun 18, 2025, 3:49 PM UTC

steveklabnik wrote: post #47

Workaccount2 wrote: post #16

Earlier quoted context omitted.

They poison their own context. Maybe you can call it context rot, where as context grows and especially if it grows with lots of distractions and dead ends, the output quality falls off rapidly. Even with good context the rot will start to become apparent around 100k tokens (with Gemini 2.5). They really need to figure out a way to delete or "forget" prior context, so the user or even the model can go back and prune…

> They really need to figure out a way to delete or "forget" prior context, so the user or even the model can go back and prune poisonous tokens. In Claude Code you can use /clear to clear context, or /compact to compact it down, with the message guiding what stays and what goes. It's helpful.

Post by nojs » Wed, Jun 18, 2025, 3:56 PM UTC

HeWhoLurksLate wrote: post #33

Workaccount2 wrote: post #16

Earlier quoted context omitted.

They poison their own context. Maybe you can call it context rot, where as context grows and especially if it grows with lots of distractions and dead ends, the output quality falls off rapidly. Even with good context the rot will start to become apparent around 100k tokens (with Gemini 2.5). They really need to figure out a way to delete or "forget" prior context, so the user or even the model can go back and prune…

I've found issues like this happen extremely quickly with ChatGPT's image generation features - if I tell it to put a particular logo in, the first iteration looks okay, while anything after that starts to look more and more cursed / mutant.

Post by kridsdale1 » Wed, Jun 18, 2025, 4:10 PM UTC

PaulHoule wrote: post #13

This was always my mental model. If you have a process with N steps where your probability of getting a step right is p, your chance of success is pᶰ, or 0 as N → ∞. It affects people too. Something I learned halfway through a theoretical physics PhD in the 1990s was that a 50-page paper with a complex calculation almost certainly had a serious mistake in it that you'd find if you went over it line-by-line. I thought…

Post by akomtu » Wed, Jun 18, 2025, 4:13 PM UTC

mtalantikite wrote: post #51

mikeocool wrote: post #2

This very much aligns with my experience — I had a case yesterday where opus was trying to do something with a library, and it encountered a build error. Rather than fix the error, it decided to switch to another library. It then encountered another error and decided to switch back to the first library. I don’t think I’ve encountered a case where I’ve just let the LLM churn for more than a few minutes and gotten a go…

I had Claude Code deep inside a change it was trying to make, struggling with a test that kept failing, and then decided to delete the test to make the test suite pass. We've all been there! I generally treat all my sessions with it as a pairing session, and like in any pairing session, sometimes we have to stop going down whatever failing path we're on, step all the way back to the beginning, and start again.

Post by kridsdale1 » Wed, Jun 18, 2025, 4:13 PM UTC

einrealist wrote: post #27

So as the space for possible decisions increases, it increases the likelihood of models to end up with bad "decisions". And what is the correlation between the increase in "survival rate" and the increase in model parameters, compute power and memory (context)?