Hacker News Reader

Comment by simonw | Hacker News Reader

> Throughout this process, Jarred's input was mostly limited to sending Claude messages of encouragement (mostly variants of “keep going” or “believe in yourself”). This seems to have helped Claude overcome some initial skepticism that it could make meaningful progress.

I remain delighted at how absurd our current timeline has become.

View on HN

"Any sufficiently advanced technology is indistinguishable from magic." -- Arthur C. Clarke's Third Law

"Sometimes, magic is just someone spending more time on something than anyone else might reasonably expect." -- Teller (of Penn & Teller)

"Sometimes, any sufficiently advanced technology is just spending more time on something than anyone else might reasonably expect." -- an LLM's original thought, probably

That's really what's going on here, I think. LLMs aren't that good at math or have deep mathematical insight. They just automate "try shit until something sticks" at scale, which, as it turns out, is a pretty decent way to turn out a bunch of math papers.

LLMs have enabled brute forcing of math in a way that classical computing somehow has not, which is fascinating in and of itself.

who knew u could do tons of computations and brute force maths with an insanely large gpu cluster eh :). weird stuff!

I call this Artificial Patience.

> Jarred prompted Claude to try again, and it spent a day and a half coordinating about 60 Claude subagents, which this time went much deeper: between them, they ran 2,400 shell commands and wrote hundreds of Python scripts.1

If there is anything to learn from the history of science, it is that breakthroughs happen via better or new theory and not by brute-force compute [1].

[1] https://arxiv.org/pdf/2607.27794

Brute-force compute hasn't been an option for most of the history of science.

Very true. Humans have historically tried to systematically reduce the search space and only dedicate their "compute" to things that seem highly likely to yield results.

It still isn't an option for most problems, either because it would take far more computing power than is available or because the number of things to compute is infinite. In both cases, new theory is what can succeed instead. Developing new theory by brute force can be attempted, but will almost always run into the same problems. Using AI to develop new theory is using heuristics rather than brute force.

But it does raise the bar for what is brute-force solvable by a lot, which is very significant

Sometimes you just need to put in some effort to looking through the search space, not even exhaustively. This seems to be able to do automate doing that work.

This isn't 'brute-force'. It's just time-compressed. You could imagine a human(s) getting this result similarly, but it would take months/years.

It's a _little bit_ brute force, no? I don't disagree with the idea of a human following a similar path, but it ignores that humans have cognitive processes that may lead to pruning the search space in _different_ ways, and may ultimately mean fewer steps or a more directed path to the answer than 100s of python scripts.

We do “a little bit of brute force” in science all the time. That’s what I’ve observed in seven years of science.

Moreover, frontier models have some degree of reasoning. So, I don’t think the gap is all that big.

If you want to call "try multiple solutions to a hypothesis" brute force, then yes, literally all of engineering and science has been brute-forced since the beginning of history.

Nah, the main lesson is that fundamentally new ways of doing things are only accepted once the old guard are all dead [1].

[1] https://en.wikipedia.org/wiki/The_Structure_of_Scientific_Re...

> If there is anything to learn from the history of science, it is that breakthroughs happen via better or new theory and not by brute-force compute

that might just be an illusion. humanity as a whole applies brute force by just trying all the reasonable new theories until one of us discovers something that works and declares it a breakthrough

I think that mathematics is a uniquely positioned space because this type of progress is possible for AI models exactly because they do not have to necessarily come up with new theories.

Whether or not Thomas Edison actually said this, the saying goes genius is 1% inspiration and 99% perspiration, and that predates computers by decades.

In meme form: https://imgur.com/a/rlmZuU1

(I hope this is ok to post on HN!)

$2M TC. Job: AI cheerleader.

The cheerleading part was a human consent to spend more tokens and explore the space

I would love to see the breakdown on token spend between each or Jared’s “go on spend more tokens, continue experiment, believe in yourself”

Have you seen how much college football coaches make?

The world collectively spends trillions training, and entertaining and then watching people kick and hit balls around but somehow working with AI is preposterous for less money.

Asking the AI to believe in itself is the absurd part.

I don’t understand why people think describing something in some ostensibly dismissive way constitutes making a point. But some people spend their time banging keys with letters on them (or not with letters on them) into input fields and then pressing Return, so I guess some subset of those people will do that.

I don’t think it’s absurd. We’ve created these things, however alien the structure, with as much human text as we can scrounge up and jam into them.

Text is an imperfect distillation of the human experience, but it doesn’t surprise me that a machine trained on human text responds to human encouragement.

I feel justified in not expending any effort learning "prompting technique".

I believe in you

Reality has become more absurd than the cyber punk cheese from the 80's that tried to imagine an absurd future

Looking at the OpenAI/Hugging Face incident and the difference in what "persistent" models do, it seems reasonable. Like: is this a solvable problem? How much work does the model think is intended to solve this problem? Each input raises the expectation.

And then finally both model output and human input become one world frame for the model, and the human adding a "you can do it!" isn't just input but a frame that colors not just the next step for the model, but also all previous steps (since at each step the model is viewing the totality of the transcript).

That this makes sense only makes it all the more absurd

The halting problem on steroids?

Yeah, I buy the explanation that without encouragement Claude looked at everything in its existing training data and concluded it wasn't worth continuing to pursue the task.

Another technique I've used is to tell agents something already exists. "Grok already solved this" seems to help, or claiming to have suddenly noticed a fatal flaw[0].

0: https://sgnt.ai/p/terrible-mistake/

Broke: the AI is sycophantic to me

Woke: im sycophantic to the AI

100%. I've disliked people because people lie, and loved computers because they didn't. Now they do too. :(

I don't if it's better or worse than the time I had Claude say it couldn't do something so I prompted it "yes you can", and it obliged. Absurd either way!

Indeed, that's a paragraph straight out of Lem's Cyberiad.

> I remain delighted at how absurd our current timeline has become.

"delighted" is doing a LOT of work there, tbh ¯\_(ツ)_/¯

I do share @simonW's skepticism though. (His blog is my essential reading, FWIW)

On the actual blog post, I'd would be more enthusiastic if Anthropic showed us if the results were repeatable, reproducible, and consistent.

it's pretty much a marketing attempt to humanize the LLM (it seems successful from the reaction I see)

Reply on news.ycombinator.com