150k lines of vibe coded Elixir: The good, the bad and the ugly
1–10 of 91 posts
Re: 150k lines of vibe coded Elixir: The good, the bad and the ugly
#2It's interesting that Claude is able to effectively write Elixir, even if it isn't super idiomatic without established styles in the codebase, considering Elixir is a pretty niche and relatively recent language.
What I'd really like to see though is experiments on whether you can few shot prompt an AI to in-context-learn a new language with any level of success.
Re: 150k lines of vibe coded Elixir: The good, the bad and the ugly
#3Great article that concretizes a lot of intuitions I've had while vibe coding in Elixir.
We don't 100% AI it but this very much matches our experience, especially the bits about defensiveness.
Going to do some testing this week to see if a better agents file can't improve some of the author's testing struggles.
Re: 150k lines of vibe coded Elixir: The good, the bad and the ugly
#4I can attest to everything. Using Tidewave MCP to give your agent access to the runtime via REPL is a superpower, especially with Elixir being functional. It's able to proactively debug and get runtime feedback on your modular code as it's being written. It can also access the DB via your ORM Ecto modules. It's a perfect fit and incredibly productive workflow.
Re: 150k lines of vibe coded Elixir: The good, the bad and the ugly
#5I can attest to everything. Using Tidewave MCP to give your agent access to the runtime via REPL is a superpower, especially with Elixir being functional. It's able to proactively debug and get runtime feedback on your modular code as it's being written. It can also access the DB via your ORM Ecto modules. It's a perfect fit and incredibly productive workflow.
Which models are you using? I’ve had mixed luck with GPT 5.2.
Re: 150k lines of vibe coded Elixir: The good, the bad and the ugly
#6It's interesting that Claude is able to effectively write Elixir, even if it isn't super idiomatic without established styles in the codebase, considering Elixir is a pretty niche and relatively recent language. What I'd really like to see though is experiments on whether you can few shot prompt an AI to in-context-learn a new language with any level of success.
You can accurately describe elixir syntax in a few paragraphs, and the semantics are pretty straightforward. I’d imagine doing complex supervision trees falls flat.
Re: 150k lines of vibe coded Elixir: The good, the bad and the ugly
#7I can attest to everything. Using Tidewave MCP to give your agent access to the runtime via REPL is a superpower, especially with Elixir being functional. It's able to proactively debug and get runtime feedback on your modular code as it's being written. It can also access the DB via your ORM Ecto modules. It's a perfect fit and incredibly productive workflow.
Which models are you using? I’ve had mixed luck with GPT 5.2.
I've been using Opus 4.5 via Claude Code
Re: 150k lines of vibe coded Elixir: The good, the bad and the ugly
#8It's interesting that Claude is able to effectively write Elixir, even if it isn't super idiomatic without established styles in the codebase, considering Elixir is a pretty niche and relatively recent language. What I'd really like to see though is experiments on whether you can few shot prompt an AI to in-context-learn a new language with any level of success.
Unless that new language has truly esoteric concepts, it's trivial to pattern-match it to regular programming constructs (loops, functions, ...)
Re: 150k lines of vibe coded Elixir: The good, the bad and the ugly
#9It seems like the 100% vibe coded is an exaggeration given that Claude fails at certain tasks.
The new generation of code assistants are great. But when I dogmatically try to only let the AI work on a project it usually fails and shots itself in its proverbial feet.
If this is indeed 100% vibe coded, then there is some magic I would love to learn!
Re: 150k lines of vibe coded Elixir: The good, the bad and the ugly
#10It's interesting that Claude is able to effectively write Elixir, even if it isn't super idiomatic without established styles in the codebase, considering Elixir is a pretty niche and relatively recent language. What I'd really like to see though is experiments on whether you can few shot prompt an AI to in-context-learn a new language with any level of success.
I would argue effectiveness point.
It's certainly helpful, but has a tendency to go for very non idiomatic patterns (like using exceptions for control flow).
Plus, it has issues which I assume are the effect of reinforcement learning - it struggles with letting things crash and tends to silence things that should never fail silently.