Is there a half-life for the success rates of AI agents? • Hacker News Board

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

#141

Post by falcor84 » Tue, Jun 24, 2025, 2:21 PM UTC

jappgar wrote: post #95

kridsdale1 wrote: post #56

Earlier quoted context omitted.

Human health follows this principle too. N is the LifeSpan. The steps taken are cell division. Eventually enough problems accumulate that it fails systemically. Sexual reproduction is context-clearing and starting over from ROM.

This is precisely why there is not and never will be a fountain of youth. Sure, you could be cloned, but that wouldn't be you. The process of accumulating memories is also the process of aging with death being an inevitability. Software is sort of like this too, hence rewrites.

> Sure, you could be cloned, but that wouldn't be you.

That's not quite clear philosophically. I like the thought experiment of them migrating each of your neurons one at a time from the biological into a computerized emulation (each emulated neuron having a physical mechanism to send proper electrical/chemical signals to those that are still biological, while doing software message passing with the digital ones) - do you at any point stop being you? Once the migration is complete and you're being fully emulated in silicon, is it still you? If they then restart the computer, is it still you after it's resumed? If they duplicate the code/weights onto two computers, are both you? And if they then reassemble your biological body with the neural connectivity based on that in the emulation - is it still you? And what if they clone the two digital "yous" into two separate bodies?

I personally don't have a clear answer to any of these, not more than I would in the plain Ship of Theseus thought experiment.

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

#142

Post by falcor84 » Tue, Jun 24, 2025, 2:29 PM UTC

emseetech wrote: post #124

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

| Making up libs This is an attack vector. Probe the models for commonly hallucinated libraries (on npm or github or wherever) and then go and create those libraries with malicious code.

Or ... if they are actually good ideas for libraries, go ahead and create them with good code, helping push the industry forward.

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

#143

Post by darrenspencer95 » Mon, Jun 30, 2025, 2:42 AM 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.

Super helpful! Thanks!