When it comes to source code, I feel like LLMs could just as well work with something like minified source code, if an LLM is trained on programming well, I think there's no reason why something like a variable should be represented by something more than a single token. Comments can be discarded, etc. In fact considering embeddings for LLMs are very rich, I think common ops could be reduced to a single token.

Imo that's why LLMs are soo good at reverse engineering. A lot of the time, assembly (with symbols) is pretty close to the source code, but compressed and encoded, and if you're familiar with the patterns of your compiler, reversing it is not that difficult.

Anyways, context engineering could be huge boon to input token curation imo (and maybe it already is)

And they said that PMSM motors are more efficient at low RPM, but their coils get saturated at higher RPMs meaning they lose efficiency at highway speeds (which actually affect the range number people car about).

So overall not such a bad tradeoff, if it makes cars less expensive.

Now they get to fill out excel sheets, babysit people and sit in planning meetings.

That, or alternatively, Mythos is so good at medical stuff, that it cam replace a lot of physician work 90% of the time, pissing off doctors, while the remaining 10% would result in very expensive lawsuits.

Imo if you don't do stuff others dont you wont end up in places others dont, which might be good or bad.

I mean, one of the biggest raises I got was when I brought my dog to the company cookout, and it turned out my boss's boss was a huge dog person, and we bonded over that, and he decided I was a good guy, which was kinda ironic as I was working my arse off to little benefit at that time.

After all, the last time I encountered Hyper-V it was in the context of copy protection that prevented crackers from observing or interfering with video game protection

We took a problem, designed an internal tool for it, and put some Bootstrap UI on top with some fancy CSS animations.

After wiring up the mock data, it looked convincigly real.

We did win, got congratulated by upper management, and were immediately asked if we could get this into production in a week, or do we need 2?

With the data structure being more efficient, and doing less overall work, I think this part of the Doom/Duke engine might even be faster than than Wolf3D

It's some prompt engineered AI harness, that guides the AI to create stats after it researches a subject and ingests the data, but I'm not sure what is it that the tool actually does on top of this.