LLMs absolutely let you explore ideas and areas you wouldn't have otherwise...but does your new design actually _work_?
I'm curious whether the "knowledge" you gained was real or hallucinatory. I've been using LLMs this way myself, but I worry I'm contaminating my memory with false information.
I think that you're confusing what you're doing with what I'm doing.
What I'm doing is learning the circuit constructs that I need and then putting them to work in real circuits. There's usually a few breadboard steps in the middle, which you could call reinforcement learning.
To me, the telling thing about your question is the implication that I would spend a week learning how to do something and then not test it out. I know that this reply reads as salty, but I'm really struggling to contain my own "wtf" on this end.
Seriously, people that are so determined to prove that LLMs don't work despite how easy it is to test for yourself and see that they clearly do work are the ones that are hallucinating.
You were on the happy path. I just had to get involved for a family member that broke their Apple phone and couldn't get their SIM transferred. Even after adding them as an authorized user under duress, they had to physically go to a T-Mobile store to get their phone on the network.
1) It can't be that replacing 20 C/C++ shared objects with 20 Rust shared objects results in 20 copies of the Rust standard library and other dependencies that those Rust libraries pull in. But, today, that is what happens. For some situations, this is too much of a memory usage regression to be tolerable.
2) If you really have 20 libraries calling into one another using C ABI, then you end up with manual memory management and manual buffer offset management everywhere even if you rewrite the innards in Rust. So long as Rust doesn't have a safe ABI, the upside of a Rust rewrite might be too low in terms of safety/security gained to be worth doing
Many Rust core/standard library functions are trivial and inlining them is not really a concern. For those that do involve significant amount of code, C ABI-compatible code could be exported from some .so dynamic object, with only a small safe wrapper being statically linked.
Meanwhile, in real life San Francisco, I much prefer being around Waymos as a pedestrian and cyclist than human drivers. While most human drivers are competent and considerate, a small percentage are not -- and given the number of encounters in a single trip, I have these dangerous interactions weekly.
Despite being a noticeable presence on the roads, Waymos have not contributed to congestion at all as far as I can tell.
He's really excellent at faking it until he makes it. That, and sucking down government funds. SpaceX, Tesla, NeuraLink, and Boring Company all relied or rely on subsidies or government contracts.
An actual car company would not have the market cap of Tesla. It's all hopes and dreams, of which Elon apparently is an excellent purveyor.
I'm curious whether the "knowledge" you gained was real or hallucinatory. I've been using LLMs this way myself, but I worry I'm contaminating my memory with false information.
reply