scwoodal

Can you share examples, links to Github of this approach? I'd like to learn.

Enforcing structured outputs from LLMs is not the same thing as using linters, formatters, static analysis to control how an agent writes code.

I would tell the LLM to write a custom rule/check for whatever the scenario is. Then when the CI gate is run, all my custom checks get deterministically run.

Elixir is where I prefer to build software, so it would be creating a custom Credo rule.

https://github.com/rrrene/credo

https://credo.hexdocs.pm/adding_checks.html

Yes it’s possible:

https://github.com/elixir-vibe/ex_dna

> I'd rather see a coding agent that can follow steps in a plan file to a T while following guardrails and adhering to the proper coding conventions in the human reviewed spec.

Guardrails/conventions should be enforced in linters, formatters, static analysis tooling; not specs/prompts.

My parents have been religiously listening to the likes of Rush Limbaugh since the early 90's on a daily basis. I recall listening to it on our drive into work together.

30+ years of hearing whatever the tv/radio host du jour says, without critical thinking, taking it at face value, 8+ hours every day. In the car to work, radio on while working, drive home, and then turn the TV on till bed time.

Then take a drive through rural America and see that education isn't an important pillar.

I went to college (neither of my parents did) and made it out with a different perspective, but my brother did not. He peddles in conspiracy theories and doesn't believe humans landed on the moon. My father regrets sending me to college.

Pretty good as others have mentioned. Even more so when one starts adding packages like credo, ex_slop, and boundary to run deterministically and steer the LLM.

Don’t like a pattern that LLM introduced? Write a custom credo rule and the problem doesn’t come back.

AI makes it trivial to narrow down who this company might have been despite the anonymized details. Mostly a heads up for future posters who want to truly avoid it.

Except after 4 gallons it might as well be pure oil, mucking everything up.

> NCAR’s climate research may not be the only thing driving the White House attack. It is widely believed to also be part of a campaign of political retribution waged against Colorado for its conviction and imprisonment of Tina Peters, a former county clerk who breached election security systems in a scheme to find proof of fraud in the 2020 presidential election. The state has included the attack on NCAR in a lawsuit against the Trump administration.

Federal policy by wounded ego is still wounded ego.

My Claude sub isn’t unlimited.

I didn’t set the limits on the plan; change those if it’s a problem, not irritate your customer base.

So I’m not allowed to use the $20 plan and max out its limits?

I’m not subletting my sub to anyone. I’m the only one using the third party harness.

I’m using their own SDK in my own CLI tool.

Why does it matter to Anthropic if my $200 plan usage is coming from Claude Code or a third party?

Doesn’t both count towards my usage limits the same?

This is correct. It just takes one person to review it and you’re good to go.

There’s also a service that rates your grammar/clarity and you have to be above a certain score.

View the projects open pull requests, and compare usernames.

https://github.com/microsoft/go-sqlcmd/pulls

The jokes write themselves. Now you can have both, Openclaw comes preloaded on the R1.

https://www.rabbit.tech/rabbit-r1

When I run into those situations I debug and try to understand why. Agent harnesses that allow you to rewind (/tree) are useful for this.

It’s often because the context is full, I gave a bad prompt or context has conflicting guidance either from direct or indirect (agents.md) prompts.

Changes introduced outside the agent window create a new state that is different from the agents.

After commands or changes are made outside of the agents doing; the agent would notice its world view changed and eventually recover, but that fills up precious context for it to bring itself up to date.

Tell it what git commands to explicitly run and in what order for your desired outcome instead of “commit everything in the worktree”

This prompt will work better across any/all models.

Hi Josh!

Scott from the Gig City conference ;)

Ash will be your Django models. Once you have models (ash resources) built; you can use the Ash ecosystem to get things like a graphql or JSON endpoint (or both!) for those resources with just a few lines of code.

I’d consider Phoenix to be like Flask. Ash fills the gap that brings Phoenix up to feature parity with a batteries included framework like Django.

Ash Admin (Django admin), Ash Resource & Domain (Django models & ORM), Ash JSON (Django Rest Framework), Ash Auth (Django Allauth), Ash Phoenix (Django Forms), Ash policies (Django permissions)

But you aren’t required to use Phoenix with an Ash project. Ash will happily work as a standalone CLI, terminal app or some other Elixir web framework that comes out tomorrow.

Isn't what you describe using your own capital to use as an investment instead of paying down the mortgage?

How do you use the leverage (debt) from the mortgage to put in a 5% investment?

The use case is a fun one liner.

+1. It's easy to drop a 1/0 wherever I want Werkzeug to show up in the browser.

> Fan motor on compressor broken, company insist everything needs changed.

Ugh, this happened to me recently.

“It’s an old system and the replacement parts can’t be found. Have to replace the whole thing. $12k”

After they leave I found a replacement on Amazon and replaced it myself 2 days later in under an hour.

I don’t think 1.7 is officially out yet as it’s sitting at rc-3.

There is no such thing as bad weather, only bad gear ;)

I also would choose Elixir/Phoenix. Having spent my career in Python/Django, Elixir/Phoenix/Live View is on another level of productivity.

For anyone needing a reason to jump into Elixir, take 40 minutes and watch this talk [1] by Sasa Juric. He communicates things so well as to all the benefits of Elixir/Erlang/BEAM.

Then take the time to read Elixir in Action book (again, Sasa) and you'll be off to the races.

[1] https://www.youtube.com/watch?v=JvBT4XBdoUE