Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Phoenix.new – Remote AI Runtime for Phoenix

fly.io

Post reply on HN
Print view View original

41–50 of 283 posts

Re: Phoenix.new – Remote AI Runtime for Phoenix

#41

Post by bee_rider »

fragmede wrote: post #19
dingnuts wrote: post #17

Earlier quoted context omitted.

since models can't reason, as you just pointed out, and need examples to do anything, and the LLM companies are abusing everyone's websites with crawlers, why aren't we generating plausible looking but non working code for the crawlers to gobble, in order to poison them? I mean seriously, fuck everything about how the data is gathered for these things, and everything that your comment implies about them. The models c…

But the models can run tools, so wouldn't they just run the code, not get the expected output, and then exclude the bad code from their training data?

That seems like a feedback loop that’s unlikely to exist currently. I guess if intentionally plausible but bad data became a really serious problem, the loop could be created… maybe? Although it would be necessary to attribute a bit of code output back to the training data that lead to it.

Re: Phoenix.new – Remote AI Runtime for Phoenix

#43

Post by pier25 »

techpression wrote: post #30
pier25 wrote: post #21

I'm surprised they are investing into this. I checked Phoenix recently because I was interested in LiveView and there isn't even an official AWS SDK for Elixir. Honestly doubt the AI stuff is going to move the needle much if you can't even have a dependable S3 client.

Considering the horror the official AWS CLI is this seems like a strange example. I’ve used both the non official libraries and they work fine. The one that is auto generated doesn’t feel very Elixir, but that’s to be expected.

> I’ve used both the non official libraries and they work fine

Maybe fine today but what about 5 years from now?

Can you say, with any degree of confidence, if these these libraries are going to be properly maintained in the future? No, you cannot.

Re: Phoenix.new – Remote AI Runtime for Phoenix

#45

Post by mcdirty »

This is great. I had to back out of a phoenix project and rewrite it in Django because I couldn't get good AI assistance. I'm pretty inexperienced with Elixir and Phoenix but understand the benefits enough to want to make projects in it. So this is really cool.

Re: Phoenix.new – Remote AI Runtime for Phoenix

#48

Post by sodapopcan »

arrowsmith wrote: post #36
erichocean wrote: post #34

Earlier quoted context omitted.

Most languages require maintenance. Some languages—Clojure is a good example—have packages from 10 years ago, entirely unmaintained, that still work great because no maintenance is needed.

This is also true for Elixir though. A lot of "unmaintained" Elixir packages still work fine.

That's their point (I think, lol).

Re: Phoenix.new – Remote AI Runtime for Phoenix

#49

Post by techpression »

pier25 wrote: post #43
techpression wrote: post #30

Earlier quoted context omitted.

Considering the horror the official AWS CLI is this seems like a strange example. I’ve used both the non official libraries and they work fine. The one that is auto generated doesn’t feel very Elixir, but that’s to be expected.

> I’ve used both the non official libraries and they work fine Maybe fine today but what about 5 years from now? Can you say, with any degree of confidence, if these these libraries are going to be properly maintained in the future? No, you cannot.

Goes for every library out there though. Official or not.
Post reply on HN