Google SWE points 48 AI agents at NASA Lidar, finds unmapped Maya pyramid in 72h

Re:Google SWE points 48 AI agents at NASA Lidar, finds unmap... by sedictious on Wednesday November 11, 2026 @08:35AM (#50453246)

I am curious how this things perform compared to a "classical" neural networks. Tasks like image classification, feature extraction has been studied extensively and there were a lot of very cool applications before (medicine included). The biggest obstacle was always data but even that could have been partly automated with some semi-supervised learning schemes. Of course the Bitter Lesson applies here, given a big enough model, it can outperform specialised ones, but at this point it's not clear 1) By how much? 2) If this is even true in the first place or if we have the means to train much leaner networks

It is becoming a boring homogenous world where we are trading deep expertise with being able to query the magic box

[ Parent | on HN ]

Re:Google SWE points 48 AI agents at NASA Lidar, finds unmap... by civvv on Wednesday November 11, 2026 @08:55AM (#50453465)

I would assume, without actually having checked, that traditional neural networks have already been extensively run on this datasets. Seems like the "standard" thing to do anyways.

My guess is that you can find 99% of Maya pyramids in a Lidar set in a fairly short time with a traditional neural network, but you might find the last few using a network of AI agents, because they are capable of "creative" problem solving and using different methods/parameters/tools over several iterations.

[ Parent | on HN ]

Re:Google SWE points 48 AI agents at NASA Lidar, finds unmap... by dist-epoch on Wednesday November 11, 2026 @09:10AM (#50453640)

The problem with specialized models is that they don't have "common sense".

You train a cat-classifier, and they will fail for a plush cat. Or maybe fail the other way, but not realizing it should also report a plush cat.

LLMs are much more robust, "find only the real cats in this picture" or "find all cats, including artificial/drawings/..."

And yes, you can add more training data to your classifier, but it's a never ending battle.

[ Parent | on HN ]

Re:Google SWE points 48 AI agents at NASA Lidar, finds unmap... by sedictious on Wednesday November 11, 2026 @10:35AM (#50454646)

You are right and I get the point (I have also worked on some solutions, though it's not my expertise), it's just that usually the people creating the ML model are supposed to substitute the creativity that the model itself does not offer. You run the model, see the false negatives and start thinking of what is missing, if there is also information that can be represented differently or can be compressed, if there is some other approach entirely. Good ML ultimately requires having deep expertise of your domain and can sometimes lead to deeper insight.

With LLM you unlock a whole new world of possibilities regarding the speed and result but we are also finding ourselves in a position where "asking the LLM" because the cheat for everything, no reason to dig further

[ Parent | on HN ]