Yes this, but unironically

We still use leaded gasoline (100LL) in prop airplanes today, for what it’s worth.

So it’s not clearly a net-negative technology.

The fact a technology is still in use does not imply that it is not negative for humanity.

I use it for many of my side projects. I just like the language, the strong typing fits well with my work.

Hype aside, if you can get an answer to a computing problem with error bars in significantly less time, where precision just isn’t that important (such as LLMs) this could be a game changer.

Precision actually matters a decent amount in LLMs. Quantization is used strategically in places that’ll minimize performance degradation, and models are smart enough so some loss in performance still gives a good model. I’m skeptical how well this would turn out, but it’s probably always possible to remedy precision loss with a sufficiently larger model though.

LLMs are inherently probabilistic. Things like ReLU throw out a ton of data deliberately.

No that isn’t throwing out data. Activation functions perform a nonlinear transformation to increase the expressivity of a function. If you did two matrix multiplications without ReLU in between, your function contains less information than with a ReLU in between.

How are you calculating "less information"?

I think what they meant was:

Two linear transformations compose into a single linear transformation. If you have y = W2(W1*x) = (W2*W1)*x = W*x where W = W2*W1, you've just done one matrix multiply instead of two. The composition of linear functions is linear.

The ReLU breaks this because it's nonlinear: ReLU(W1*x) can't be rewritten as some W*x, so W2(ReLU(W1*x)) can't collapse either.

Without nonlinearities like ReLU, many layers of a neural network could be collapsed into a single matrix multiplication. This inherently limits the function approximation that it can do, because linear functions are not very good at approximating nonlinear functions. And there are many nonlinearities involved in modeling speech, video, etc.

I had a Palm Pre and really enjoyed this, shame it didn’t make it.

Feels like maybe this is retreading ground covered by Why3ML, but perhaps I’m missing something.

https://www.why3.org/doc/whyml.html

Presumably this is aimed at people that want to take advantage of it in Lean.

My favorite diagramming tool hands-down! It’s the only one that’s ever “clicked” for me, I use it all the time.

Maybe other folks’ vibe coding experiences are a lot richer than mine have been, but I read the article and reached the opposite conclusion of the author.

I was actually pretty impressed that it did as well as it did in a largely forgotten language and outdated platform. Looks like a vibe coding win to me.

Sure it did ok with examples that are easily found in a text book like drawing a circle.

Im pretty new to CC, been using it in a very interactive way.

What settings are you using to get it to just do all of that without your feedback or approval?

Are you also running it inside a container, or setting some sort of command restrictions, or just yoloing it on a regular shell?

So CC has a planning mode. Shift-Tab twice to enter planning mode. I wrote out about a paragraph of text for this and it gave me back a todo list. I said "make it so" and it went and did it.

Let us know how the security audit by human beings on the output goes.

It's really just a personal project for myself. Why else would I add that feature without any guardrails?

The auditors are using llms too!

nginx and Roblox and redis and nmap and neovim and cryengine … the list goes on

There are a LOT of tools with embedded Lua scripting capabilities.

Not having to put length-1 everywhere is a good thing, actually.

Probably just use a .last method or something. Reads better too.