Thanks for making this! Helps simplify it nicely
Show HN: LlamaGym – fine-tune LLM agents with online reinforcement learning
11–20 of 29 posts
Re: Show HN: LlamaGym – fine-tune LLM agents with online reinforcement learning
#12When 150 lines of boilerplate can land you the first page on HN, maybe it is, in fact, the end of programming?
Re: Show HN: LlamaGym – fine-tune LLM agents with online reinforcement learning
#13When 150 lines of boilerplate can land you the first page on HN, maybe it is, in fact, the end of programming?
Let's not be one of those people who measure developer productivity by number of lines
Re: Show HN: LlamaGym – fine-tune LLM agents with online reinforcement learning
#14When 150 lines of boilerplate can land you the first page on HN, maybe it is, in fact, the end of programming?
Karpathy’s micrograd [1] is literally 154 lines. Guess programming ended 4 years ago.
Re: Show HN: LlamaGym – fine-tune LLM agents with online reinforcement learning
#15When 150 lines of boilerplate can land you the first page on HN, maybe it is, in fact, the end of programming?
I’m not really sure what your point is. Is it not remarkable that valuable things can be done in 150 lines?
Re: Show HN: LlamaGym – fine-tune LLM agents with online reinforcement learning
#16When 150 lines of boilerplate can land you the first page on HN, maybe it is, in fact, the end of programming?
Carmack's infamous fast inverse square root was only 13 lines. Measuring code by line metrics rather than its contents reflects shallow, questionable comprehension.
Re: Show HN: LlamaGym – fine-tune LLM agents with online reinforcement learning
#17I want to make a Discord bot that impersonates all my friends and continues to refine the model as the conversations continue. Basically this [1] post, but with a more modern model and, ideally, reinforcement learning. Seems like this would fit the bill.... Is there anything else that would make this easier?
Re: Show HN: LlamaGym – fine-tune LLM agents with online reinforcement learning
#18When 150 lines of boilerplate can land you the first page on HN, maybe it is, in fact, the end of programming?
I’m not really sure what your point is. Is it not remarkable that valuable things can be done in 150 lines?
I agree with you. / Above, I wouldn't assume a single nor clearly intended "point". Reading it I got an impression more of concern, even fear. I'm guessing one underlying driver may be a concern that AI is creeping into more and more programming. Which is true.
Re: Show HN: LlamaGym – fine-tune LLM agents with online reinforcement learning
#19Re: Show HN: LlamaGym – fine-tune LLM agents with online reinforcement learning
#20Could someone help me understand the kinds of things you can build with this? Is this like RLHF?