1. nate_nowack Aug 21, 2025 parent

   yea i dont think there's any blocker from a protocol perspective, im just saying i'd love to see it happen. adoption for sure among the largest hurdles id guess
2. nate_nowack Aug 20, 2025 parent

   would love fb marketplace disruptor on atproto
3. nate_nowack Apr 10, 2025 parent

   yea its a popular DX at this point: https://blog.alternatebuild.dev/marvin-3x/
4. nate_nowack Apr 10, 2025 parent

   no https://bsky.app/profile/alternatebuild.dev/post/3lg5a5fq4dc...
5. nate_nowack Mar 6, 2024 parent

   yeah this seems to be pretty much the same interface as `fn` from marvin, except w/o pydantic (see https://github.com/PrefectHQ/marvin?tab=readme-ov-file#-buil...)
6. nate_nowack Mar 6, 2024 parent

   as with marvin, you can just swap the base url and use any of the oss proxy libs that clone the openai api (but since they don't do function calling [except for mistral i think], its not as good afaik)
7. nate_nowack Apr 9, 2023 parent

   hi, just seeing this!

   you're correct that normal chatgpt wouldn't crawl the URL, but ai_fns can have plugins like the DuckDuckGo plugin / VisitURL plugin which can be invoked by the underlying Bot if it decides its helpful to its answer

   for example: https://gist.github.com/zzstoatzz/a16da0594afc2bb751428907e4...

   feel free to try it yourself :)

8. nate_nowack Mar 30, 2023 parent

   interesting! I hadn't seen that before

   ai_fn is just a specific way to use Marvin's Bot abstraction, which is one of the few abstractions Marvin offers

   but a couple differences I notice off the bat between ai_fn and com2fun:

   - marvin uses pydantic for parsing LLM to result types

   - you can pass plugins/personality/instructions to the underlying bot via the @ai_fn decorator kwargs

   - (unless I'm missing a dataclass version of this in com2fun) marvin can parse output into arbitrary pydantic types like this example https://github.com/PrefectHQ/marvin/issues/106#issuecomment-...

9. nate_nowack Mar 30, 2023 parent

   Hi!

   This example was produced using GPT 3.5 turbo, where yes, the LLM does not always align ideally. I used 3.5 for the example since that's Marvin's default and I know many people wouldn't have gpt4 access yet (which is significantly better at following instructions) - didn't want to set a misleading expectation.

   that said, my instructions for the bot in this example certainly could have been more precise :) for a more real example, you could check out the other example (which works pretty well on 3.5) https://github.com/PrefectHQ/marvin/blob/main/examples/load_...

This user hasn’t submitted anything.