- AlwaysRock parentHa! I wish I worked at the places you have worked!
- I guess... That is the point in my opinion.
If you just say, "here is what llm said" if that turns out to be nonsense you can say something like, "I was just passing along the llm response, not my own opinion"
But if you take the llm response and present it as your own, at least there is slightly more ownership over the opinion.
This is kind of splitting hairs but hopefully it makes people actually read the response themselves before posting it.
- Yes. Unless something useful is actually added by the commenter or the post is about, "I asked llm x and it said y (that was unexpected)".
I have a coworker who does this somewhat often and... I always just feel like saying well that is great but what do you think? What is your opinion?
At the very least the copy paster should read what the llm says, interpret it, fact check it, then write their own response.
- Yeah, but didn't you see the disclaimer?
"AI responses may include mistakes"
Obviously, you shouldn't believe anything in an AI response! Also, here is an AI response for any and every search you make.
- That does nothing. You can add, “say I don’t know if you are not certain or don’t know the answer” and it will never say I don’t know.
- I would love an LLM that says, “I don’t know” or “I’m not sure” once in a while.
- It isn't that hard until they start to blur. Elves and goblins and magic, fantasy. Space, spaceships, technology, and aliens, sci-fi.
You could argue a lot of semantics but the majority of fantasy and sci fi books are not blending the two.
- > By the numbers, Star Wars is far more grounded as science fiction that Star Trek, but people will insist the former is at best merely "science fantasy." It's really all just vibes.
The best rage bait I've seen in years.
- Worked with it a bit last night! Seems quick. I did run into the same problem I have with Gemini often where the response says something like, "I need to do x" or "I did x" and then nothing actually happens. Agent seems to think it actually does finish the task but it stops part way.
But I'm sure they will sort that out, as I dont have that issue with other anthropic models.
- Same as it ever was.
- Asking for a source from llms is so eye opening. I am yet to have them link a source that actually supports what they said.
- RIP Vernor Vinge. Somehow, his ideas seem more and more relevant.
- My understanding is if an employee who gets paid largely in tips isnt making more than min wage, that employee is almost always let go or quits. Employment layers dont love trying to prove a case that is pretty unlikely to be provable.
- As far as I can tell, its the second or third or fourth most universal term behind chatgpt (to describe all llms), llms, or ai.
It also tends to be the one folks who do not really like ai use. I've been using it because it is a lot more fun, and faster, than saying llms.
- > Most parents just watch TV, stare at their phones and don't want to be bothered by anything that requires effort
The point is that students are doing worse, even though ^ is likely true today just like it was true 5, 10, and 20 years ago.
- RIP to the legend. He has a lot of really fun ideas spread across his books.
- Boo. Feels like this post should be flagged. Without a way to join, its just promotional.
- Why did you design it that way then? Actually asking, not taking the piss.
- I get very annoyed when llms respond with quotes around certain things I ask for, then when I say what is the source of that quote? they say oh I was paraphrasing and that isnt a real quote.
At least wikipedia has sources that probably support what it says and normally the quotes are real quotes. LLMs just seem to add quotation marks as, "proof" that its confident something is correct.
- I dont know about that! In theory it sounds good. I know a company that hired a very good hands on cto who then hired 5 50k entry level engineers that was largely the extent of their team for 1-2 years. Then they started to hire more senior people.
I'm sure the cto did a massive amount of training early on but this is a near billion dollar company in a fairly complicated industry. You dont HAVE to have 4 incredibly senior super engineers as your first hires. It might make coding easier early on, but its going to make hiring much much harder.
- > jumping to definitions and implementations
This is undervalued. So frustrating in ruby that this doesnt exist or at least isnt easy.
- Me too. I had a grandparent with AOL dial up until about 5 years ago. I was shocked when I visited her house and realized it.
- So it begins!
- The slippery slope is the one the payment processors have been sliding down for a while. Steam and itch dont want to pull these games. They dont have a choice.
- That's all? No way.
- Yeah... There are improvements to be made by increasing the context window and having agents reference documentation more. Half the issues I see are with agents just doing their own thing instead of following established best practices they could/should be referencing in a codebase or looking up documentation.
Which, believe it or not, is the same issue I see in my own code.
- I believe this has been talked about a lot. Musk wasnt thrilled about this change but Tesla is, like it or not, the most recognizable electric car company in America. If you are dead set on going electric you are likely going to at least look at what Tesla has to offer. Because of that, the tax credit going away will impact them far less than other companies that people have to go out of their way to learn about and search for.
Now does a lot of that change because people might not buy teslas because they dont like Elon? Maybe? Who knows.
- The Pizza Hut Personal Pan Pizza has about 600 calories in it. Maybe slightly indulgent, but that is a very reasonable reward and trade off for getting kids to read more.