Hacker News: scwoodal

New comment by scwoodal in "GLM 5.2 vs. Opus"

scwoodal — Mon, 22 Jun 2026 14:44:53 +0000

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

New comment by scwoodal in "GLM 5.2 vs. Opus"

scwoodal — Mon, 22 Jun 2026 14:33:57 +0000

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

New comment by scwoodal in "GLM 5.2 vs. Opus"

scwoodal — Mon, 22 Jun 2026 13:29:01 +0000

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

New comment by scwoodal in "GLM 5.2 vs. Opus"

scwoodal — Mon, 22 Jun 2026 10:29:04 +0000

Yes it’s possible:

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

New comment by scwoodal in "GLM 5.2 vs. Opus"

scwoodal — Mon, 22 Jun 2026 10:04:11 +0000

> 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.

New comment by scwoodal in "Measles surge in Utah sparks fears US could undo decades of progress"

scwoodal — Sun, 14 Jun 2026 16:31:38 +0000

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.

New comment by scwoodal in "Phoenix LiveView 1.2"

scwoodal — Sun, 14 Jun 2026 14:26:39 +0000

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.

New comment by scwoodal in "The worst job interview I ever had"

scwoodal — Wed, 27 May 2026 12:15:11 +0000

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.

New comment by scwoodal in "1M context is now generally available for Opus 4.6 and Sonnet 4.6"

scwoodal — Sat, 14 Mar 2026 01:30:37 +0000

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

New comment by scwoodal in "White House plan to break up iconic U.S. climate lab moves forward"

scwoodal — Thu, 12 Mar 2026 20:00:34 +0000

> 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.

New comment by scwoodal in "Anthropic officially bans using subscription auth for third party use"

scwoodal — Thu, 19 Feb 2026 04:45:40 +0000

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.

New comment by scwoodal in "Anthropic officially bans using subscription auth for third party use"

scwoodal — Thu, 19 Feb 2026 04:21:14 +0000

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

New comment by scwoodal in "Anthropic officially bans using subscription auth for third party use"

scwoodal — Thu, 19 Feb 2026 04:08:54 +0000

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.

New comment by scwoodal in "Anthropic officially bans using subscription auth for third party use"

scwoodal — Thu, 19 Feb 2026 04:00:44 +0000

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?

New comment by scwoodal in "15 years later, Microsoft morged my diagram"

scwoodal — Wed, 18 Feb 2026 09:16:52 +0000

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.

New comment by scwoodal in "AI is destroying open source, and it's not even good yet"

scwoodal — Tue, 17 Feb 2026 03:05:42 +0000

View the projects open pull requests, and compare usernames.

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

New comment by scwoodal in "OpenClaw is changing my life"

scwoodal — Sun, 08 Feb 2026 16:48:33 +0000

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

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

New comment by scwoodal in "Claude Opus 4.6"

scwoodal — Sat, 07 Feb 2026 09:29:47 +0000

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.

New comment by scwoodal in "Claude Opus 4.6"

scwoodal — Sat, 07 Feb 2026 09:18:15 +0000

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.

New comment by scwoodal in "Claude Opus 4.6"

scwoodal — Fri, 06 Feb 2026 11:54:07 +0000

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.