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

151–160 of 283 posts

Re: Phoenix.new – Remote AI Runtime for Phoenix

#151

Post by losvedir »

This is very neat, and right up my alley as both someone really into Elixir and who thinks agentic AI is the future.

I have a question about how you manage context, and what model you use. Gemini seems the best at working with give context windows right now, but even that has its limitations. Thinking about working with Claude Code, a fair bit of my strategizing is in breaking down work and managing project state to keep context size manageable.

I'm watching the linked video and it's amazing seeing it in action, but I'm imagining continuing to work on a project and wondering if it will start losing its way so to speak. Can you have it summarize stuff, and can you start a session clean with those summaries, and have it "forget" files it won't need to use for this next feature, etc?

Re: Phoenix.new – Remote AI Runtime for Phoenix

#152

Post by pier25 »

sysashi wrote: post #146
pier25 wrote: post #120

Earlier quoted context omitted.

Not only large enterprise customers. Anyone who's thinking mid or long term.

Why do you need an official SDK to make http calls?

Why do you even need a framework like Phoenix? Just write everything yourself! /s

Re: Phoenix.new – Remote AI Runtime for Phoenix

#153

Post by mwcampbell »

krainboltgreene wrote: post #106
yunwal wrote: post #103

Earlier quoted context omitted.

The same logic that would lead one to believe that AI is anti-worker should also lead one to believe that software as a whole is anti-worker.

Sure, if you don't think about it at all.

The argument you're responding to is effective enough, based solely on the fact that it has led me to second-guess whether I chose the right line of work, that it would be worth expounding on what you think is wrong with it.

Re: Phoenix.new – Remote AI Runtime for Phoenix

#154

Post by vaer-k »

CollinEMac wrote: post #39

I'm a little surprised by the sentiment here that LLMs don't do well with Elixir. I've had a pretty good experience using AI tools on Phoenix/Elixir side projects.

I've only used LLMs with Elixir, so I don't have any other experience for comparison, but I've found that although Claude frequently employs the wrong approaches in Elixir, I usually know when he'll have trouble and just ask him to read pertinent documentation first. So long as he's read the manual he seems to do just fine.

Re: Phoenix.new – Remote AI Runtime for Phoenix

#155

Post by tptacek »

rustc wrote: post #44

"Sign in with fly.io" takes me to a page asking me to pay $20 but the plan details are vague - what exactly is included in "$20/mo of Built-In AI Assistance Builds, refactors, and debugs right in your IDE"?

This is a situation where we've been pushing on Chris to get this out into the world quickly, and there's a lot of packaging stuff like this that isn't fully put together yet. Thanks for calling it out! We'll get to it over the next week.

Re: Phoenix.new – Remote AI Runtime for Phoenix

#156

Post by olafura »

pier25 wrote: post #120
Snakes3727 wrote: post #100

Earlier quoted context omitted.

Neither of them are official which is often a non starter for some large enterprise customers.

Not only large enterprise customers. Anyone who's thinking mid or long term.

I still don't understand this. If you are big enough then you get Amazon to make an official sdk, if you aren't then what exactly are you looking for?

The official aws cli used to talk to the soap interface and used regex instead of actually doing correct error handling and that was used by so many tools. Even though it used to break horrible.

It's quite a niche you are talking about, not big enough to debug open source code but still big enough to require SLA for SDK and not being able to talk Amazon into creating it. It's generated code, it's not rocket science.

What I have experienced is that software licence, where you are sending data to, where you are hosting it and having access to audit the code has usually been a bigger concern.

But then again big organisations often have really specific concerns. So I'm not doubting your statement it's just that I have never heard it before.

Re: Phoenix.new – Remote AI Runtime for Phoenix

#157

Post by krainboltgreene »

jonator wrote: post #148
krainboltgreene wrote: post #104

Earlier quoted context omitted.

I know what stories workers in the industry are using to cope with working with capitalists that have explicit goals of eliminating workers. I'm sure your poor understanding of the history of improved tooling, like "type writer secretaries", will be a soft comfort in the future.

And you don't think capitalism is the reason we have these computer jobs to automate away in the first place?

No, because I’ve read a history book.

Re: Phoenix.new – Remote AI Runtime for Phoenix

#159

Post by quaunaut »

pier25 wrote: post #120
Snakes3727 wrote: post #100

Earlier quoted context omitted.

Neither of them are official which is often a non starter for some large enterprise customers.

Not only large enterprise customers. Anyone who's thinking mid or long term.

The main lib everyone uses, :ex_aws, has been actively maintained for literally over a decade[1]. Official or not, it's used by literally the entire community, since even non-AWS services often will support its API.

1. https://github.com/ex-aws/ex_aws/releases?page=2

Re: Phoenix.new – Remote AI Runtime for Phoenix

#160

Post by indigodaddy »

So is Phoenix.new a Fly.io product, or just under the fly umbrella? Also, is pricing clearly laid out anywhere (including what the additional costs are for permanently deployed/hosted services that arise from Phoenix) ? Didn't dig too hard admittedly, but wasn't obvious where to find or look for pricing information on the front page on mobile
Post reply on HN