Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

tobyord.com

Post reply on HN
Print view View original

31–40 of 143 posts

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

#31

Post by bluefirebrand »

vadansky wrote: post #23
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 a particularly hard parsing problem so I setup a bunch of tests and let the LLM churn for a while and did something else. When I came back all the tests were passing! But as I ran it live a lot of cases were still failing. Turns out the LLM hardcoded the test values as “if (‘test value’) return ‘correct value’;”!

This is the most accurate Junior Engineer behavior I've heard LLMs doing yet

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

#32

Post by nico »

qazxcvbnmlp wrote: post #7
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…

when this happens I do thew following 1) switch to a more expensive llm and ask it to debug: add debugging statements, reason about what's going on, try small tasks, etc 2) find issue 3) ask it to summarize what was wrong and what to do differently next time 4) copy and paste that recommendation to a small text document 5) revert to the original state and ask the llm to make the change with the recommendation as cont…

> 1) switch to a more expensive llm and ask it to debug

You might not even need to switch

A lot of times, just asking the model to debug an issue, instead of fixing it, helps to get the model unstuck (and also helps providing better context)

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

#33

Post by HeWhoLurksLate »

Workaccount2 wrote: post #16
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…

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.

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

#34

Post by rvnx »

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.

I've noticed something, even if you ask to edit a specific picture, it will still used the other pictures in the context (and this is somewhat unwanted)

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

#35

Post by esafak »

prmph wrote: post #17

The amusing things LLMs do when they have been at a problem for some time and cannot fix it: - Removing problematic tests altogether - Making up libs - Providing a stub and asking you to fill in the code

If humans can say "The proof is left as an exercise for the reader", why can't LLMs :)

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

#36

Post by nico »

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…

> Rather than fix the error, it decided to switch to another library

I’ve had a similar experience, where instead of trying to fix the error, it added a try/catch around it with a log message, just so execution could continue

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

#37

Post by nico »

prmph wrote: post #17

The amusing things LLMs do when they have been at a problem for some time and cannot fix it: - Removing problematic tests altogether - Making up libs - Providing a stub and asking you to fill in the code

- Adding try/catch block to “remove” the error and let execution continue

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

#38

Post by alganet »

peacebeard wrote: post #18
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…

Very common to see in comments some people saying “it can’t do that” and others saying “here is how I make it work.” Maybe there is a knack to it, sure, but I’m inclined to say the difference between the problems people are trying to use it on may explain a lot of the difference as well. People are not usually being too specific about what they were trying to do. The same goes for a lot of programming discussion of c…

> People are not usually being too specific about what they were trying to do. The same goes for a lot of programming discussion of course.

In programming, I already have a very good tool to follow specific steps: _the programming language_. It is designed to run algorithms. If I need to be specific, that's the tool to use. It does exactly what I ask it to do. When it fails, it's my fault.

Some humans require algorithmic-like instructions too. Like cooking a recipe. However, those instructions can be very vague and a lot of humans can still follow it.

LLMs stand on this weird place where we don't have a clue in which occasions we can be vague or not. Sometimes you can be vague, sometimes you can't. Sometimes high level steps are enough, sometimes you need fine-grained instructions. It's basically trial and error.

Can you really blame someone for not being specific enough in a system that only provides you with a text box that offers anthropomorphic conversation? I'd say no, you can't.

If you want to talk about how specific you need to prompt an LLM, there must be a well-defined treshold. The other option is "whatever you can expect from a human".

Most discussions seem to juggle between those two. LLMs are praised when they accept vague instructions, but the user is blamed when they fail. Very convenient.

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

#39

Post by PaulHoule »

bwfan123 wrote: post #25
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…

> 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. Interesting, and I used to think that math and sciences were invented by humans to model the world in a manner to avoid errors due to chains of fuzzy thinking. Also, formal…

These were symbolic calculations. Mine was a derivation of the Gutzwiller Trace Formula

https://inspirehep.net/files/20b84db59eace6a7f90fc38516f530e...

using integration over phase space instead of position or momentum space. Most people think you need an orthogonal basis set to do quantum mechanical calculation but it turns that "resolution of unity is all you need", that is, if you integrate |x>There are quite a few calculations in physics that involve perturbation theory, for instance, people used to try to calculate the motion of the moon by expanding out thousands of terms that look like (112345/552) sin(32 θ-75 ϕ) and still not getting terribly good results. It turns out classic perturbation theory is pathological around popular cases such as the harmonic oscillator (frequency doesn't vary with amplitude) and celestial mechanics (the frequency to go around the sun, to get closer or further from sun, or to go above or below the plane of the plane of the ecliptic are all the same.) In quantum mechanic these are not pathological, notably perturbation theory works great for an electron going around an atom which is basically the same problem as the Earth going around the Sun.

I have a lot of skepticism about things like

https://en.wikipedia.org/wiki/Anomalous_magnetic_dipole_mome...

in high energy physics because frequently they're comparing a difficult experiment to an expansion of thousands of Feynman diagrams and between computational errors and the fact that perturbation theory often doesn't converge very well I don't get excited when they don't agree.

----

Note that I used numerical calculations for "unit and integration testing", so if I derived an identity I could test that the identity was true for different inputs. As for formal systems, they only go so far. See

https://en.wikipedia.org/wiki/Principia_Mathematica#Consiste...

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

#40

Post by ffsm8 »

vadansky wrote: post #23
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 a particularly hard parsing problem so I setup a bunch of tests and let the LLM churn for a while and did something else. When I came back all the tests were passing! But as I ran it live a lot of cases were still failing. Turns out the LLM hardcoded the test values as “if (‘test value’) return ‘correct value’;”!

Missed opportunity for the LLM, could've just switched to Volkswagen CI

https://github.com/auchenberg/volkswagen

Post reply on HN