41–47 of 47 posts
Earlier quoted context omitted.
[flagged]
Are you being paid to post here? They're giving me nothing. Cheapskates.
Earlier quoted context omitted.
Yeah the meaning was what I said until about 2 weeks ago when someone went viral talking about air travel without a cellphone. Do vulgarities often become accepted?
Some of them do, yes. Tone policing has always been around as well, just surprises me to happen in an online forum about "vulgarities".
I'd also avoid saying "So. How are we going to fuck this pig?" in a meeting about infra problems.
Earlier quoted context omitted.
Yeah the meaning was what I said until about 2 weeks ago when someone went viral talking about air travel without a cellphone. Do vulgarities often become accepted?
Are we allowed to say "sex" or "kill"? Or do we have to start s*lf-c*nsoring everything? Anyway, my last search to how to un-alive children processes gave me nothing. I wonder if those m*n pages are actually wr*tten by pr*f*ss*n*ls.
and you jest but there's been pushes to change things like "master/slave", "kill", "whitelist/blacklist", and the like to something different. I don't know how much traction, and i may have been tricked by april 1st posts or something.
Earlier quoted context omitted.
> Seems like the LLM is giving correct output if it’s generating a plausible string of tokens in response to your string of tokens. No. If you prompt it to get a response and then you ask it to cite sources, if it outputs broken links that never existed then it clearly failed to deliver correct output.
"correct" for an llm means "fits the statistical distributions in the training data" "correct" for you is "truth that corresponds to the real world" They are two very different things. The llm's output is, very much, correct. Because it was never meant to mean anything other than similarity of probability distributions. It's not what you wanted, but that doesn't make it incorrect. You're just under a wrong assumption…
Earlier quoted context omitted.
> Seems like the LLM is giving correct output if it’s generating a plausible string of tokens in response to your string of tokens. No. If you prompt it to get a response and then you ask it to cite sources, if it outputs broken links that never existed then it clearly failed to deliver correct output.
Seems that's just expecting things that LLMs were not designed for. It's a token producer based on trained weights, it doesn't use any sources. Even if it were "fixed" so that it only generates URLs that exist, it's still incorrect because it did not use any sources so those URLs are not sources.
Earlier quoted context omitted.
Or why the LLM doesn’t do a lookup into a subset of the training data as a database and reject the output if it seems to be wrong. A billion of the most urls and the entirety of Wikipedia, arkiv and stackoverflow would go a long way.
If that could be done, then we would be using that and skipping the llms entirely
Earlier quoted context omitted.
If that could be done, then we would be using that and skipping the llms entirely
Can’t see why that couldn’t be done? You save a http request for a ton of the urls.