1 - a markov chain only takes previous tokens as input.

2 - It uses a function (in the mathematical sense, so same input results in same output, completely stateless) to generate a set of probabilities for what the next token might be.

3 - The most probable token is picked, else randomness (temperature) is inserted here to choose a different token occasionally.

an llm’s internals, the part that’s trained is literally the function used in step 2. You could have this function implemented a number of ways, ex you could build a huge table and consult it. Or you could generate it somehow. You could train a big neural network that takes previous tokens as input, and outputs probabilities of tokens as output. You then enumerate its outputs for every possible permutation of inputs and there’s your table. This would take too much time and space, so we just run the function on-demand instead. Exact same result. It can be very smart and notice correlations, but ultimately it generates a (virtual) huge static table. This is a completely deterministic process. A trained NN is still a (huge) mathematical function. So the big network that they spend resources training is basically the function used in step 2.

Step 3 is the cause of hallucinations. It’s the only nondeterministic part. And it’s not part of the llm itself in any way. No matter how smarter the neural network gets, the hallucinations are introduced mainly in step 3. So no, they won’t be solving the LLM hallucination problem anytime soon.

they already tried. remember uwp?

and that is exactly how a predictive text algorithm works.

• some tokens go in

• they are processed by a deterministic, static statistical model, and a set of probabilities (always the same, deterministic, remember?) comes out.

• pick the word with the highest probability, add it to your initial string and start over.

• if you want variety, add some randomness and don’t just always pick the most probable next token.

Coincidentally, this is exactly how llms work. It’s a big markov chain, but with a novel lossy compression algorithm on its state transition table. The last point is also the reason why, if anyone says they can fix llm hallucinations, they’re lying.

deleted by creator

you almost always get better efficiency at scale. If the same work is done by lots of different machines instead of one datacenter, they’d be using more energy overall. You’d be doing the same work, but not on chips specifically designed for the task. If it’s already really inefficient at scale, then you’re just sol.

no but you could have 2 jobs and still work less.

morning coffee, break, afternoon coffee, go home

deleted by creator

titles are easy. just use figlet and be done with it.

What I did appreciate more was diagrams and maps done in ascii. Those had to have been done by hand

but it very probably was not a memory error. Rust isn’t magic. It probably could not have prevented this bug anyway.

They said it was a “logic error”. so i think it was more likely some divide by zero or something like that

a new generation of developers needs to pad out their resume

the virus definition is not written in c++. And even then, the problem was that the file was full of zeros.

no, you didn’t. It just told you it did

yuge!

if they don’t have access to install keyloggers then you don’t need to protect yourself from them.

EEEEEEEidle eidle EEEEEEEE!!!

except the portal keeps popping up whenever I touch my controller, and the remember option does not work. It pops up in the foreground anytime I even accidentallytouch my contoller’s touchpad. In home streaming is basically impossible for me rn.

No, they are not. If someone has enough access to install a keylogger, then they can just grant permission to themselves. This is mostly security theater, trying to turn desktops into phones.

i switched to porkbun from godaddy specifically because of this.