11–20 of 45 posts
But it also seems like a strange, incestuous, closed system approach.
Like, unless you are introducing something new into the system, you just have the system churning against itself, probably until it reaches an equilibrium (or else becomes incoherent).
Earlier quoted context omitted.
Not really. Pretty much the "killer app" feature of ChatGPT is RLHP. Whether or not the current RLHP-ed Alpca really beats ChatGPT, it is pretty obvious that local LLMs can be RLHP-ed and it is only a matter of time before people realize running an RLHP-ed LLM locally is a better option than running ChatGPT with all the security concerns of running something "in the cloud" (which is just "somebody else's computer" in…
I’m sorry what’s RLHP? I’m not able to Kagi that
Earlier quoted context omitted.
Not really. Pretty much the "killer app" feature of ChatGPT is RLHP. Whether or not the current RLHP-ed Alpca really beats ChatGPT, it is pretty obvious that local LLMs can be RLHP-ed and it is only a matter of time before people realize running an RLHP-ed LLM locally is a better option than running ChatGPT with all the security concerns of running something "in the cloud" (which is just "somebody else's computer" in…
I’m sorry what’s RLHP? I’m not able to Kagi that
Took me a bit of searching too.
Absolutely off topic, but I just got back from a week in Peru, where the alpaca is a prominent member of the local fauna. For folks in the US at least, it's a relatively inexpensive trip and an absolutely gobsmackingly gorgeous country with friendly people and amazing food. Highly recommended!!!
Hm. Title: “beats Chat GPT” Reality: > With these evaluation instructions, we compare RLHF model responses to Davinci003 responses and measure the fraction of times the RLHF model is preferred; we call this statistic the win-rate. > Of the methods we studied, PPO proves the most effective, improving the win-rate against Davinci003 from 44% to 55% according to human evaluation, which even outperforms ChatGPT. …for the…
The measure is win rate versus DV3. Their model wins more often than ChatGPT Beating a weaker player more often is not evidence of being able to beat a stronger player on average though
It improved the simulated win rate vs human win rate?
…but chatgpt had a higher win rate overall? (And gpt4 was much higher)
What is the significance of the difference between simulated and human win rates?
I wonder how much longer this "Using LLMs to evaluate the quality of other LLMs" can last. Certainly it has proven valuable and useful up until now, especially since ChatGPT is a pretty high bar to evaluate against. But it also seems like a strange, incestuous, closed system approach. Like, unless you are introducing something new into the system, you just have the system churning against itself, probably until it re…
RLHF is supervised learning on top of unsupervised learning. Is supervised learning at some point of the process a requirement for all reasonable ML models?
Earlier quoted context omitted.
The measure is win rate versus DV3. Their model wins more often than ChatGPT Beating a weaker player more often is not evidence of being able to beat a stronger player on average though
What does “win” mean though? It improved the simulated win rate vs human win rate? …but chatgpt had a higher win rate overall? (And gpt4 was much higher) What is the significance of the difference between simulated and human win rates?
You should try asking what you don’t know in a non judgemental manner
I wonder how much longer this "Using LLMs to evaluate the quality of other LLMs" can last. Certainly it has proven valuable and useful up until now, especially since ChatGPT is a pretty high bar to evaluate against. But it also seems like a strange, incestuous, closed system approach. Like, unless you are introducing something new into the system, you just have the system churning against itself, probably until it re…
I wonder how long "Using humans to rate the quality of other humans" thing can last. Surely academia has only so long before it collapses.