321–329 of 329 posts
Earlier quoted context omitted.
To be fair, this should probably be covered by basic physics/maybe cooking classes. “You can’t determine the calories in food by looking at it” isn’t really ML specific.
Won't help much if kids are ai'ing their way through physics then ten years later need to go on a diet having not applied the knowledge possibly ever or exercised their critical thinking skills
Earlier quoted context omitted.
Considering the lack of basic math skills I encounter each and every day, I don't think schools did enough; they certainly aren't going to do enough w/LLMs.
Knowing the lack of understanding of basic chemistry and physics like fundamental thermodynamics... I have little hope any population can be trained to understand LLMs sufficiently...
Earlier quoted context omitted.
I am asking a lot here, but school needs to be training people what AI is and what it's weaknesses are and how to use it... My school taught me to use a calculator. It also taught me how to check my work when I relied on the calculator. AI is a very complicated calculator - you give it an input, magic happens, it gives you an output. Really no different, to a layman.
It's more complicated than a calculator. Even researchers who have dedicated their lives to the field don't know all of the limitations of any given model. That fact alone isn't helpful when a model is 80% correct in one area but 2% in another.
Earlier quoted context omitted.
that is good to know. presented this way i find LLM behavior to be a feature, not a bug. then again i think everything is value add over pen and paper / notepad / spreadsheet and maybe a friend or doctor (or specialized equipment if you need more than calorie in, calorie out). just go exercise and don't be a lard lad
> just go exercise and don't be a lard lad You can out-exercise almost any diet, but it takes 3-4 hours a day of a hard workout. If calories in, calories out was useful advice rather than a banal statement of physics, nobody would be fat.
i prefaced for those who have legit medical issues
more people adopt your "banal" viewpoint and are just lazy
c-r vibe coding
It’s just an impossible problem. Photons don’t provide sufficient information to determine calories (at least not in any way they could practically be captured). Inside that sandwich could be drenched with olive oil or it could be hollow cheese with lettuce. It’s impossible to tell.
And what if that guy in the surveillance video is just 2 kids in a trench coat? There's no way for AI to be sure from the photons: we should scrap it.
Earlier quoted context omitted.
> just go exercise and don't be a lard lad You can out-exercise almost any diet, but it takes 3-4 hours a day of a hard workout. If calories in, calories out was useful advice rather than a banal statement of physics, nobody would be fat.
go run 30 minutes a day and get back to me i prefaced for those who have legit medical issues more people adopt your "banal" viewpoint and are just lazy c-r vibe coding
LLMs seem really bad with reading numbers and reporting them back. I’m building a game, and to se how well its docs were being indexed, I tried asking simple questions to ChatGPT, Gemini, whatever Microsoft’s thing is, etc: “What is the armour value for the Leather Shirt” in the game Stravaeger?” It confidently got it wrong. “You can find the game at https://stravaeger.com ” Different confident answers, also wrong. “…
AIs are still computer programs and are not given the resources to render javascript, so they cannot access the game data from the website. And they obviously don't have it in their parameters. BTW Google Gemini Pro just told me that they know the game but did not know the value. Actually, it points out that it is a known trap for AI to confidently give a wrong, hallucinated value. Maybe it had already seen this thread and integrated it in their parameters or fine tuning. I don't know...
Gemini Fast confidently gives me a wrong value. But very quickly! I'll attach the entire Gemini response as a sub-reply.
LLMs seem really bad with reading numbers and reporting them back. I’m building a game, and to se how well its docs were being indexed, I tried asking simple questions to ChatGPT, Gemini, whatever Microsoft’s thing is, etc: “What is the armour value for the Leather Shirt” in the game Stravaeger?” It confidently got it wrong. “You can find the game at https://stravaeger.com ” Different confident answers, also wrong. “…
Are you building the site from the same json files that are used in the game? AIs are still computer programs and are not given the resources to render javascript, so they cannot access the game data from the website. And they obviously don't have it in their parameters. BTW Google Gemini Pro just told me that they know the game but did not know the value. Actually, it points out that it is a known trap for AI to con…
LLMs seem really bad with reading numbers and reporting them back. I’m building a game, and to se how well its docs were being indexed, I tried asking simple questions to ChatGPT, Gemini, whatever Microsoft’s thing is, etc: “What is the armour value for the Leather Shirt” in the game Stravaeger?” It confidently got it wrong. “You can find the game at https://stravaeger.com ” Different confident answers, also wrong. “…
Are you building the site from the same json files that are used in the game? AIs are still computer programs and are not given the resources to render javascript, so they cannot access the game data from the website. And they obviously don't have it in their parameters. BTW Google Gemini Pro just told me that they know the game but did not know the value. Actually, it points out that it is a known trap for AI to con…
It’s literally ’gameconstants.js’ with an item list that has a .name string and a .armor value that it could look up. But when I pointed it to the file and told it which row to read from, still chose to make something up instead of read the data designed to be read by computers.
I do like how your ai tries to cover for its buddies with lies about there not being any documentation online. Because pointing AIs to a specific page and asking them to read the numbers there is a known trap.