i mainly use it for fact checking sources from the internet and looking for bias. i double check everything of course. beyond that its good for rule checking for MTG commander games, and deck building. i mainly use it for its search function.
I've been using o3-mini mostly for ffmpeg command lines. And a bit of sed. And it hasn't been terrible, it's a good way to learn stuff I can't decipher from the man pages. Not sure what else it's good for tbh, but at least I can test and understand what it's doing before running the code.
Deepseek is pretty good tbh. The answers sometimes leave out information in a way that is misleading, but targeted follow up questions can clarify.
I just use it to write emails, so I declare the facts to the LLM and tell it to write an email based on that and the context of the email. Works pretty well but doesn't really sound like something I wrote, it adds too much emotion.
This is what LLMs should be used for. People treat them like search engines and encyclopedias, which they definitely aren't
If you want an AI to be an expert, you should only feed it data from experts. But these are trained on so much more. So much garbage.
This is not correct. Even if trained on purely peer-reviewed and published math papers, it will still make math errors.
Which one?
which of what category?
I’m confused. Are you saying all AI models are bad at math, or one in particular? You’re speaking broadly, so I assume the former.
Broadly. All AI models are bad at math. By math I mean mathematical reasoning, not arithmetic. (It's already well-known they're bad at arithmetic unsupplemented.)
Actually -- they're pretty good at math as far as a typical undergrad goes. But they still make a lot of mistakes; 40% of the time is not an unreasonable estimate, depending on use case.
This, but for tech bros.
People tweeting stuff. We allow tweets from anyone.
RULES:
