[Escapade5160]

I've been saying for a while that given a proper harness, small local models can perform incredibly well. When you have a system that can try everything, it will eventually get it right as long as you can prevent it from getting it wrong in the meantime.

[zambelli]

Lol, I love that framing. Yeah, the small models have impressed me a lot during this work. The reasoning can be quite good, and definitely sufficient for a lot of cases. Just gotta nudge em back on track Every now and then and they'll figure it out.

[Aurornis]

The problem is that you get similar quality as if you gave a junior unlimited time to work on a problem and told them to keep trying different things until the goal is reached.

Even the SOTA models have this problem when the work is complicated enough. The problem is amplified more with the small models.

[coip]

One important facet of this is it’s not far from “giving unlimited juniors unlimited time…”

Where the limits are set by hardware for agentic execution (compute/network/storage) && inference speed

[Zetaphor]

There's a lot of valuable things that can be done in that range, especially when token costs aren't a concern. Not every problem requires SOTA

[Aurornis]

> especially when token costs aren't a concern. Not every problem requires SOTA

If token costs aren’t a concern I’m using SOTA for everything.

Even SOTA gets it wrong and hallucinates, but at a lower rate. I don’t want to waste my time.

[lixquid]

I believe they mean token costs aren't a concern when you're not paying for a SOTA model via API, and are instead running local models.

Infinite monkeys on infinite typewriters, and all that.

[Zetaphor]

Correct, I have local hardware, not infinite money.

[cornholio]

If I understood correctly, the model will get it right because it knows when it isn't right.

[zambelli]

Essentially, yes that's right! There's some subtlety in how to let it know it was wrong (returning things as tool errors because it trained on that), but that's the gist of it - sort of a self-correcting architecture.

[tomjakubowski]

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

[jon_richards]

I was expecting this https://knowyourmeme.com/memes/the-missile-knows-where-it-is

[forlorn_mammoth]

the missile knows where it is because it knows where it isn't

[andai]

Prior art: https://ghuntley.com/ralph/

[koolba]

A thousand monkeys on a thousand typewriters…

[zambelli]

That is the whole challenge, actually! A new metric I'm going to dogfood into forge is ETTWS - estimated time to working solution.

A simple retry loop around your whole workflow could, in some cases, be all you need. But it could mean many blind attempts to get through a workflow successfully. And hopefully there isn't a payment step partway through!

The fewer hard errors nix the whole workflow, the lower your ETTWS.

[killing_time]

Is it strange that I immediately interpreted ETTWS to be Estimated Time To William Shakespeare?

[Mithriil]

It's relevant to the "thousand monkeys on a thousand typewriters".

[jononor]

The one true AGI metric!

[beacon294]

Have you read the MAKER/MDAP paper? 1 million sequential tasks.

[zambelli]

No, I haven't - hadn't heard of it. I'll try to squeeze in a quick read in the coming weeks!

[DiogenesKynikos]

This is a thousand unusually smart monkeys who speak every major human language fluently and are proficient in every major programming language, but sometimes still make bizarre mistakes and need to be put back on track.

[jplusequalt]

This is fun for you?

[bratbag]

I found it fun to read.