clutter55561

VSCode is the last editor, pi is the last harness, blah, blah blah

Nonsense. The losses will be swallowed by the government, i.e. the tax payers, in the name of “National Interest”.

My 2-cents: never install those things into your host. A locked down Docker container is the bare minimum. Pin your versions and never update them without checking the changelog.

Don’t get too excited, Claude code still won’t detect skills on .agents/skills.

From their changelog:

2.1.277

September 18, 2026

Added AGENTS.md support: in a project with no CLAUDE.md, Claude Code reads AGENTS.md instead; change it under “Project instructions” in /config (not yet on Bedrock, Vertex or Foundry)

Note that this *does not include .agents/skills*. Argh.

Yes, I’d read it.

But beware of opinions.

Don’t let people put you down, especially here in HN, where people are perceived to smart. Smart doesn’t equal sensible or unbiased.

Many books are written to scratch the itch of the author. Just like an open source project. It is a work of love.

At the end of the day, it is my job as a parent to steer my kids out of harm’s way, be it the alley where they will find the local dealer, the park where people are injecting at night, or not stuffing their faces with sugar, or social media.

The “Bob and Alice are technically illiterate” defence doesn’t hold. I’m gun illiterate but I wouldn’t buy one for my kids.

Do I feel bad for the kid that killed himself doing something stupid he say at TikTok? Yes. Do I feel bad the for parents that gave a phone with TikTok to an unsupervised 11 year old? Not really.

Parents must take responsibility.

This wins the internet this week!

Claude Code is not just a harness. It is a different product. You pick the smallest subscription that allows you to do your work. My “multiplier” on a $100 subscription is 5+.

If you’re using API, on the other hand, there is absolutely no reason to use Claude Code, or Codex.

I use both Claude and Codex, but mostly Claude for planning and coding, and Codex to review Claude’s work.

I follow a sort of waterfall workflow which is verbose but fully transparent.

Anthropic’s $100 subscription works fine for me, but whatever subscription my company has with OpenAI reaches the 5hr limit ridiculously quickly.

ORMs have their place but they are leaky as hell. RDMSs are very diverse, have different languages, and require different optimisation techniques.

ORMs that try to paper over all the differences fail miserably. They become super complicated and generally produce crap SQL.

ORMs also tend to oversimplify database design. They are just tables with primary keys, right? Who needs indices? Who needs to think about collation? God forbid anyone mentions physical organisation of the data!

Having said this, I do use a very small subset of SQLAlchemy (the bits I understand) in data pipelines.

Great stuff, well done and super useful!

Tools that remove the fat seem like a good idea, but I’m highly suspicious of their effect on the LLM’s reasoning.

LLMs were trained in the typical full-fat output found everywhere on the internet, and all of sudden they get a slightly different response that may look like nothing they have seen before.

Does that really save tokens in the long run?

Not exactly. Apple kept it for existing users but stopped offering it to new users. So new users are vulnerable.

I think this is very interesting but you need a better slogan.

Many people here made comments such as “why do I need another SVC since agents are pretty good with git”, which means they barely read your blurb and did not understand your project.