• 5 Posts
  • 191 Comments
Joined 2 年前
cake
Cake day: 2025年2月24日

help-circle
  • Had to read “Animal, Vegetable, Miracle” for an environmental science class, which is what initially got me interested in gardening. That prompted me to read “Gaia’s Garden,” which is a permaculture book. I like a lot of the basic principles of permaculture, but a lot of stuff isn’t science or evidence based, and a lot of stuff is taken from indigenous practices without acknowledging it.







  • Yes, but large amount of resources are put into controlling and influencing the population. It’s a fight, and we aren’t fighting back enough. It’s my opinion the problem is systemic, and merely trying to be more mindful of consumption isn’t going to improve things much (it will improve things some, and people should do it). For instance, there’s a good chance those cage-free eggs involved some sort of very low-paid and abused workers. There is no ethical consumption under capitalism.




  • I don’t think Harris was progressive at all. She seemed disingenuous, media-trained to be as uncontroversial as possible, and every talking point focus tested. Her major economic policy was to give more money to business owners. I think Waltz is somewhat progressive, and they did put a leash on him. I agree she would’ve won if she was more progressive, especially if she focused on policies benefiting labor.










  • I think tool calling is just a form of structured output, where the LLM outputs something like json that describes the function to call and the arguments, then you parse that and run the function with the arguments, then feed the output back to the LLM in a new message, if you want. IDK the specific details, I’m guessing there are some special tokens some LLMs produce for tool calling, and I’m also guessing there is “controlled generation” (masking the logits/tokens, and only choosing to generate the tokens that would be valid). Ollama apparently doesn’t support the special tool-calling tokens or output structure that some models use.

    This is how it looks when using OpenAI compatible APIs: https://platform.openai.com/docs/guides/function-calling?api-mode=responses.

    I’ve never heard of TabbyAPI (I’m new to using local models, in general). I’m also not sure what TabbyAPI brings over Ollama, llama.cpp, or vLLM. So would be curious as well.

    Edit: For my little toy project I’m working on, I’m switching to not using tool-calling at all, and building a LangGraph and using structured output, which should be more reliable with my use-case. I.e. just always call the tool manually, feed the output back to the LLM to have the LLM evaluate if the output was correct, retry calling the tool with different arguments if not, and just fail after 5 calls.

    I like watching Yannic Kilcher, to keep up with some of the newer developments, and read various papers. I do have a background in ML (mostly the more traditional, non-generative, supervised learning and reinforcement learning) though.



  • I think this is only a small part. Interest rates are kinda high. VCs only want to invest in companies with AI exposure because of all the hype. From companies I’ve interviewed with, offshoring seems to have accelerated dramatically (companies only had or wanted a few US devs to manage larger Indian teams). I’ve visited career pages of companies working in the business domain I have the most experience with, and all open software positions are exclusively in India.