346
this post was submitted on 25 Mar 2024
346 points (98.3% liked)
Technology
59631 readers
2718 users here now
This is a most excellent place for technology news and articles.
Our Rules
- Follow the lemmy.world rules.
- Only tech related content.
- Be excellent to each another!
- Mod approved content bots can post up to 10 articles per day.
- Threads asking for personal tech support may be deleted.
- Politics threads may be removed.
- No memes allowed as posts, OK to post as comments.
- Only approved bots from the list below, to ask if your bot can be added please contact us.
- Check for duplicates before posting, duplicates may be removed
Approved Bots
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
No. A lot of times I'm looking to compare many answers. I'll give you an example.
If I want to look for interesting barbecue rubs that I haven't tried before I'll query a search engine. Historically (not so much recently) Google has been better at searching through forums than a direct forum search. So I can check many different sources for the ratios people are using and make my decision.
Google's half baked AI is really terrible right now. It has a memory of about two answers, barely understands context, and hallucinates more often than both copilot and ChatGPT.
Now I'm looking for a coffee rub and it's giving me injection advice (happened when I tested Gemini), it gets barbecue styles mixed up, doesn't follow dietary restrictions that are explicitly stated, and will give you recipes for the wrong cut and type of meat.
It's not ready, and anyone trusting it for an answer to a question is going to have a bad time. If you have to verify it by checking a bunch of links anyway then it's not only worthless, it's making search take longer and take up screen real estate.
Wooooo what?
Brisket coffee rub is fairly common. I only know one guy who uses a coffee injection because it's not common, although other injections are pretty common for brisket.
I have no idea why it went off on that particular tangent. I guess whatever barbecue data it was trained on had a lot of injection advice along with the coffee rubs.