andreasronge
What happens if you design tools for LLMs instead of letting LLM use human tools ?
Wrote a blog on why and what that enables.
As I see it the LLM has very different requirements on languages, runtimes and libraries.
For example it’s rather crazy that we often allow the LLM use a general purpose language and the operating system. But I also believe that the LLM will actually gain power by restricting its capabilities.
Trending in Blog Posts
Up until then, I found it very hard to communicate to LLMs that I specifically do not want to handle X case because maybe it has never ha...
New
An automated trigger fired every two minutes for 8 hours. 243 agent runs. 31M tokens. $63 wasted. The problem: nobody noticed until morni...
New
TL;DR: Give https://cure-lang.org a try—perhaps you will like it.
New
I finally found time to write down my journey away from ExMachina, including the workaround I tried first and the API experiments that fo...
New
The words are insufficient to describe what transpired. What we tried to do met what the people wanted it to be. It became beautiful.
Th...
New
Hi all,
I’ve built a small demo app to understand what an “AI agent” actually is under the hood, and to show it with Elixir’s own tools ...
New
A backtest worker and a live trading node had to share one broker rate limit and one set of OAuth tokens, and both only work if there’s e...
New
Other Trending Topics
A little off-topic, but I feel like people here have a good head on their shoulders.
I used to be quite good at making software. Was luc...
New
Hey. Is there anyone here who creates agents in their apps? Not talking about using agents, but creating them. I’m finding it pretty diff...
New
I fully migrated to my own harness from Anthropic/Gemini and I think it’s time to share it. Welcome DSH, the DeepSeek Harness, fully writ...
New
Beam Bots (or just BB for short) is a framework for building fault-tolerant robotics applications in Elixir using familiar OTP patterns. ...
New
There has been a thread to discuss the Stack Overflow Developer Survey on this forum every year since 2018, so here’s yet another one for...
New
I love Elixir. It’s one of 2 programming languages I’ve ever fallen in love with.
But I don’t use it anymore.
Serverless was the promis...
New
Categories:
Sub Categories:
Forums
Popular Tags
- #ecto
- #liveview
- #troubleshooting
- #learning-elixir
- #library
- #deployment
- #erlang
- #testing
- #genserver
- #mix
- #absinthe
- #remote-other
- #otp
- #plug
- #how-to-question
- #macros
- #postgres
- #elixirconf
- #channels
- #exunit
- #discussion
- #code-sync
- #podcasts
- #javascript
- #onsite
- #dialyzer
- #docker
- #authentication
- #umbrella
- #ai
- #full-time-contract
- #podcasts-by-brainlid
- #ecto-query
- #blog-post
- #elixirconf-us
- #elixir-ls
- #phoenix_html
- #iex
- #graphql
- #genstage
- #websockets
- #supervisor
- #advent-of-code
- #distillery
- #processes
- #elixirconf-eu
- #api
- #forms
- #security
- #metaprogramming











Showing Posts 1 to 4- Show Best Posts
- Show All (oldest first)
- Show All (newest first)
rhcarvalho
Loved how it circles back to Lisp
Clojure is indeed a good modern pick. If you don’t know it already, have a look at babashka, it’s “Clojure to replace bash scripts”, maybe that brings some inspiration.
Another nice Lisp/Scheme-derived language is Racket, which might be less “practical” but may also provide insights.
andreasronge
Thanks. Yes I do use Babashka as the oracle for Clojure conformance tests. Will check Racket.
Btw, there seems to be more devs that comes to the same conclusion regarding Lisp is a good fit, I learned about these today:
AgentScript
and sema-lang
For me the interesting thing is the BEAM runtime and what that allows the agents safely to do that human developers would never do (e.g. fan out 100+ REPLs)
dimitarvp
Clojure is great but the JVM startup time is a tough pill to swallow for scripts. Maybe through another runtime, or if they began compiling to native code like Racket does, then it’d be worth another look.
rhcarvalho
Have a look at babashka.