Most of my searches have to do with video games, and I have yet to see any of those AI generated answers be accurate. But I mean, when the source of the AI's info is coming from a Fandom wiki, it was already wading in shit before it ever generated a response.
People Twitter
People tweeting stuff. We allow tweets from anyone.
RULES:
- Mark NSFW content.
- No doxxing people.
- Must be a pic of the tweet or similar. No direct links to the tweet.
- No bullying or international politcs
- Be excellent to each other.
- Provide an archived link to the tweet (or similar) being shown if it's a major figure or a politician.
I’ve tried it a few times with Dwarf Fortress, and it was always horribly wrong hallucinated instructions on how to do something.
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.
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
That sounds like more work than just writing the email to me
Yeah, that has been my experience so far. LLMs take as much or more work vs the way I normally do things.
This, but for tech bros.
Deepseek is pretty good tbh. The answers sometimes leave out information in a way that is misleading, but targeted follow up questions can clarify.
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.