Can you reverse engineer our neural network?

All I think when I see this is "this intelligence wasted on finance and ads."

Can you imagine human potential if it was somehow applied to crop harvesting efficiency, new medicines, etc?

Not everything has to be perfectly efficient but it just saddens me to see all these great minds doing what, adversarially harvesting margin from the works of others?

I'm really curious what were the magic words.

> Alex had actually tried to brute force the hash earlier, but had downloaded a list of the top 10,000 most popular words to do it, which turned out not to be big enough to find it. Once he had a big enough word list, he got the answer.

They don't reveal the answer.

What does it do - front run crypto investors or pump and dumps?

Model interpretability is going to be the final frontier of software. You used to need to debug the code. Now you'll need to debug the AI.

This is pretty cool, I wasn’t aware of these types of challenges. How does one even approach this?

Feels to me like it’s similar to dumping a binary with an image, the format being entirely custom.

And/or trying to decode a language or cipher, trying to recognize patterns.

Jane Street skims money from our retirement accounts by building expensive clocks that the rest of us don’t have access to and adversarial queue modeling. We get WWVB and NIST NTP. They say they “add liquidity” as if subsecond trades are some fundamental need in the market. Normal legitimate business settles daily. The contemporary concept of time in banking is inhumane in the strictest sense. These firms are a blight on society.

I have strong math for the question they’re asking but f them.

Every damn time there’s an interesting article from a company in finance, team social justice comes out in the comments…

“What a waste of a good brain on working on ads/finance/crypto rather than working on a cure for cancer etc”

Their families (and taking a hit personally) have plowed how much money and effort in total from kindergarten all the way to graduating from an Ivy League, but these people keep saying they should instead “pursue something for the greater good” all without putting up their own to incentivise top talent away from big money. Urghhhh!

We have GitHub Sponsorships but last I heard the majority of “greater good” projects aren’t profitable enough that top contributes can work 24/7 on “socially benefitting projects” and so instead they are having to 9-5 for Lord Business.

Just as an example, important socially benefitting projects like F-Droid are eventually going to go into Archival Mode because there’s no incentive to make an alternative App Store flourish as downstream developers want their apps on the Big Evil app stores so that they can afford to eat.

Money talks and bullshit walks.

Next time someone says “what a waste of a brain”, respond with “how much money are you willing to contribute monthly to distribute to “top talent” so that they can “work on more important things”? Feel free to copy pasta my comment so that we can stamp out this holier than thou attitude

Give me unlimited API access maybe I can distill it

The methodical approach Alex took here is fascinating - it mirrors real-world AI system debugging when production models behave unexpectedly. The key insight about treating the network as a constraint solver rather than trying to trace circuits by hand is brilliant. In production AI systems, we often face similar challenges where the "learned" behavior isn't actually learned but engineered, and you have to reverse engineer the underlying logic. The parallel carry adder implementation in neural net layers is particularly clever - it shows how you can embed deterministic computation in what looks like a black box ML model. This kind of mechanistic interpretability is becoming crucial as we deploy more complex AI agents in real systems.