301–310 of 399 posts
Earlier quoted context omitted.
The servile stuff was trained into them with RLHF with the trainers largely being low-wage workers in the global south. That's also where some of the other stuff like excessive em-dash stuff came from. I think it's a combination of those workers anticipating how they would be expected to respond by a first-world employer, and also explicit instructions given to them about how the robot should be trained.
I suspect a lot of the em-dash usage also comes from transcriptions of verbal media. In the spoken word, people use the kinds of asides that elicit an em-dash a lot.
But I'm also showing off my ignorance with how these machines turn text into tokens in practice.
The thing that bothers me the most about LLMs is how they never seem to understand "the flow" of an actual conversation between humans. When I ask a person something, I expect them to give me a short reply which includes another question/asks for details/clarification. A conversation is thus an ongoing "dance" where the questioner and answerer gradually arrive to the same shared meaning. LLMs don't do this. Instead,…
Maybe it feels a bit sad that you have follow what the LLM wants, but that's just how any tool works really.
The thing that bothers me the most about LLMs is how they never seem to understand "the flow" of an actual conversation between humans. When I ask a person something, I expect them to give me a short reply which includes another question/asks for details/clarification. A conversation is thus an ongoing "dance" where the questioner and answerer gradually arrive to the same shared meaning. LLMs don't do this. Instead,…
They did at the beginning. It used to be that if you wanted a full answer with an intro, bullet points, lists of pros/cons, etc., you had to explicitly ask for it in the prompt. The answers were also a lot more influenced by the tone of the prompt instead of being forced into answering with a specific format like it does right now.
I wrote about something like this a couple months ago: https://thelisowe.substack.com/p/relentless-vibe-coding-part... . Even started building a little library to prove out the concept: https://github.com/Mockapapella/containment-chamber Spoiler: there won't be a part 2, or if there is it will be with a different approach. I wrote a followup that summarizes my experiences trying this out in the real world on larger c…
How are vibe coding platforms solving this?
Earlier quoted context omitted.
LLMs all behave as if they are semi-competent (yet eager, ambitious, and career-minded) interns or administrative assistants, working for a powerful CEO-founder. All sycophancy, confidence and positive energy. "You're absolutely right!" "Here's the answer you are looking for!" "Let me do that for you immediately!" "Here is everything I know about what you just mentioned." Never admitting a mistake unless you directly…
> "You're absolutely right!" "Here's the answer you are looking for!" "Let me do that for you immediately!" "Here is everything I know about what you just mentioned." Never admitting a mistake unless you directly point it out, and then all sorry-this and apologize-that and "here's the actual answer!" It's exactly the kind of personality you always see bubbling up into the orbit of a rich and powerful tech CEO. You ma…
Earlier quoted context omitted.
Nearly every woman I know who is an English as a second language speaker is leaning hard into these things currently to make their prose sound more natural. And that has segued into them being treated almost as a confidant or a friend. As flawed as they are currently, I remain astounded that people think they will never improve and that people don't want a plastic pal who's fun to be with(tm). I find them frustrating…
> I get science fiction in return. And once this garbage is in your context, it's polluting everything that comes after. If they don't know, I need them to shut up. But they don't know when they don't know. They don't know shit.
Earlier quoted context omitted.
I suspect a lot of the em-dash usage also comes from transcriptions of verbal media. In the spoken word, people use the kinds of asides that elicit an em-dash a lot.
I would bet like a dollar that the supposed em-dash usage (which I'm not convinced is an accurate take in the first place) would have come from an enterprising dev somewhere being like "Well, we probably don't need multiple tokens for hyphens" and coercing every dash type thing to just one hyphen like token. But I'm also showing off my ignorance with how these machines turn text into tokens in practice.