News for hackers. Stuff that matters.

nate_nowack

Re:Introduction to Bluesky's AT Protocol on Wednesday August 20, 2025 @09:23PM (#44968164)
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
Re:Introduction to Bluesky's AT Protocol on Wednesday August 20, 2025 @04:46PM (#44966259)
would love fb marketplace disruptor on atproto
Re:smartfunc: Turn Docstrings into LLM-Functions on Thursday April 10, 2025 @01:00PM (#43645892)
yea its a popular DX at this point: https://blog.alternatebuild.dev/marvin-3x/
Re:Show HN: Fructose, LLM calls as strongly typed functions on Wednesday March 06, 2024 @02:40PM (#39620337)
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...)
Re:Show HN: Fructose, LLM calls as strongly typed functions on Wednesday March 06, 2024 @02:36PM (#39620277)
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)
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 :)

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-...

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_...