I have used both GPT-4o and Claude 3.5 for writing elixir, and in my opinion Claude is better. I consider starting paid plan to get access to Claude 4.
Wojciech
sbuttgereit
I’ve been using Claude 3 Opus and more recently 3.5 Sonnet via Source graph Cody. It’s pretty good, though I wish the in editor completion suggestions would allow partial acceptance… I find that often times the first bits are pretty good, but it gets worse the longer the suggestion is.
I do find that the Elixir support is pretty good and it can be helpful mostly in refactoring and, documenting things (except style can get inconsistent.). But for me the killer app aspect are certain tasks that are not really about Elixir. For example.. I hate writing shell scripts (mostly because I suck at it): AI to the rescue… My shell scripts are infrequent and small enough that it actually hits a sweet spot for LLMs just producing a completely competent final result (just never trust that it’s so)… Same thing with regular expressions. Those things alone are worth the subscription.
I’ve tried OpenAI gpt 4o and just found I preferred Claude’s results better.
4
preciz
That modal was just a simple example I gave but of course I have used it for more complex things. One of my favorite is to /add a file I just created and ask it to write tests for it. Then I edit the tests it created if necessary. This way I write more tests and save a lot of time.
It is capable to do meta programming correctly, change code from runtime to compile time etc. it did a lot of things for me.
Overall it’s good enough to save time and boost productivity for most programmers I would say.
1
lud
Coding with the voice is my dream 
Do you pay for Anthropic ? I can see this pricing:
Input $3 / MTok
Output $15 / MTok
How much do you pay every month and/or how far can you go with the free plan ?
edit: I’m trying to claim the free $5 credits to try with an anthropic API key but it does not work …
1
Zurga
I know, and I’m glad it can do these things. I was just wondering whether Claude was able to do more complex stuff.
Are these simple refactors deterministic? So if it is refactoring multiple files, is it going to do it the same way each time.
I tried it with the example question in my earlier post, and it did not seem to quite grasp what i meant.
ChatGPT seems to be going in the right direction: ChatGPT - Recording LiveView Interactions
1
preciz
Determinism is a matter of the seed value and temperature settings of the inference, which I don’t configure. But I believe that aider is taking care of these optimally already.
I think we can’t expect that proprietary models will be deterministic but if you use aider with a lcoal one like deepseek coder v2 you can control it more.
However I must mention that it’s not a matter of importance for me anymore that the model gives back the same code always. Through usage that turned out not to be as important as it presents itself at first.
0
preciz
Currently on average I see ~150K token in and ~20K tokens out per day.
This is mixed in with our team mates aider usage and that we use the API also through Open WebUI for chatting.
So personal usage when coding with Elixir should be just <10$ per month. Of course, that’s an estimation.
1
lud
tozz
Can echo what people in the thread has already said, Claude 3.5 Sonnet outperforms 4o by far when it comes to Elixir, even comes with syntax highlighting.
I have cancelled my OpenAI subscription and will go with an Anthropic subscription instead.
2
cpursley
This combo is just insane (Claude blows GPT out of the water - maybe off the planet). I’ve never been more productive. And I feel like the UX is still not totally figured out - looking forward to how it evolves.
2