Hacker News new | past | comments | ask | show | jobs | submit
MangoCoffee | on: Claude Opus 4.8
ChatGPT came out in 2022. Back then it was just a chatbot. Now we have AI agents. What matters is how we use them and how the agents get better. That’s what will move AI forward.
zozbot234 | parent | next
An 'AI agent' is just a chatbot that is told to type commands on a REPL-like interface as part of its system prompt. It's still processing pure text-based requests and responses, they're just not restricted to natural language.
arbitrandomuser | root | parent | next
A lot of people dont know this , also the chatbot (chatgpt) itself is a next token predictor (the GPT) that's been given an initial text that says " pretend to be a chatbot .." and asked to complete it , the coherant chatting behaviour is something thats emergent .

later on someone figured if you asked it to output a reasoning before it gave a response its output would have more logical coherence, as though the reasoning output tokens functioned as a scratch space for it to work on.

at the end its all next token prediction

hellohello2 | root | parent | next
No, chatbots are LLMs trained for question-answering through RLHF (its not just a prompt). But yes, if you just zero-shot prompt a bare LLM you can still "talk to it" & you are correct on everything else as far as I know.
fragmede | root | parent
At lot of people don't know this, also the human brain is a squishy lump of meat. that's been given a childhood and the prompt "act like an adult", and asked to behave. The coherant chatting behaviour is something thats emergent .

later on someone figured if you shove Adderall in it and it to think before it speaks, it gave a response its output would have more logical coherence, as though the Adderall concentration drugd functioned as a scratch space for it to work on.

in the end its a squishy lump of meat.

loading story #48317349
loading story #48316371
hellohello2 | root | parent | next
They are chatbots trained for tool use, its not just a prompt.
sigmarule | root | parent | next
An AI agent and a chatbot are both applications built using LLM inference as a primitive.
furyofantares | root | parent | next
Yeah and a car is just an engine connected to wheels.
smj-edison | root | parent
Yeah. LLMs are fundamentally a batch-based system, and we smear a veneer of liveness and autonomy on top.
MattDamonSpace | parent
Not even 4 years old yet. This tech curve has been insane
rzmmm | root | parent | next
I still use LLM in quite similar way as when ChatGPT was launched. There has been progress but I think the real leap was 2020-2022.
SoftTalker | root | parent | next
Not even the typical lifecycle of a corporate PC or laptop. It is pretty wild.
dakolli | root | parent
Yet no productivity gained except for people who love to produce mediocre work at a rapid pace. Which is many of you I guess. I don't see any rapid progress being made in any science of importance. You people are all falling for a marketing trap.

Have fun betting your competency on the quality and quantity of tokens you have access too. Hate to break it to you, but the billionaires aren't going to keep renting you $2mm in GPUs for 5 hours a day for $200.00 a month forever.