Hacker News: throwaway7783

New comment by throwaway7783 in "US and Iran agree to provisional ceasefire"

throwaway7783 — Wed, 08 Apr 2026 02:26:58 +0000

So we go and say "a whole civilization will die tonight".

New comment by throwaway7783 in "German police name alleged leaders of GandCrab and REvil ransomware groups"

throwaway7783 — Mon, 06 Apr 2026 16:47:36 +0000

Isn't this just the good old "aka"?

New comment by throwaway7783 in "Artemis II crew see first glimpse of far side of Moon [video]"

throwaway7783 — Mon, 06 Apr 2026 01:14:44 +0000

There is an opportunity cost to everything. Moving money from energy research to food programs may mean not having an energy breakthrough that could potentially cut down food costs (and a lot of other things) dramatically in the long run.

New comment by throwaway7783 in "Artemis II crew see first glimpse of far side of Moon [video]"

throwaway7783 — Mon, 06 Apr 2026 01:09:58 +0000

The poem itself seems to mix several things (It is a poem, and can say whatever it wants of course). What parent said doesn't preclude medical care as a right for a concept, though.

Also, a cursory search says around 2 trillion are spent on healthcare (effectively or not is irrelevant in this context) and NASA moon exploration costs $90B. Doesn't feel like these are all mutually exclusive.

New comment by throwaway7783 in "The future of version control"

throwaway7783 — Sun, 22 Mar 2026 21:50:52 +0000

Yep. This is the only model that has worked well for me for more than a decade.

New comment by throwaway7783 in "Britain is ejecting hereditary nobles from Parliament after 700 years"

throwaway7783 — Wed, 11 Mar 2026 22:34:07 +0000

Does House of Lords have any real power today?

New comment by throwaway7783 in "Agents that run while I sleep"

throwaway7783 — Wed, 11 Mar 2026 17:39:20 +0000

Yep, not saying we don't need skills. Just harnesses.

New comment by throwaway7783 in "Agents that run while I sleep"

throwaway7783 — Wed, 11 Mar 2026 01:19:25 +0000

You don't need most of this. Prompts are also normally what you would say to another engineer.

* There is a lot of duplication between A & B. Refactor this.

* Look at ticket X and give me a root cause

* Add support for three new types of credentials - Basic Auth, Bearer Token and OAuth Client Creds

Claude.md has stuff like "Here's how you run the frontend. here's how u run backend. This module support frontend. That module is batch jobs. Always start commit messages with ticket number. Always run compile at the top level. When you make code changes, always add tests" etc etc

New comment by throwaway7783 in "Agents that run while I sleep"

throwaway7783 — Wed, 11 Mar 2026 01:15:27 +0000

I agree with this. There is not a lot of harnesses/wrapping needed for Claude Code.

New comment by throwaway7783 in "Agents that run while I sleep"

throwaway7783 — Wed, 11 Mar 2026 01:14:18 +0000

We have a very uncomplicated setup with claude code. A CLAUDE.md with instructions and notes about the repo and how to run stuff. We also do code reviews with Claude Code, but in a separate session.

It works wonderfully well. Costs about $200USD per developer per month as of now.

New comment by throwaway7783 in "Agents that run while I sleep"

throwaway7783 — Wed, 11 Mar 2026 01:12:32 +0000

Regarding the self-congratulation machine - I simply use a different claude code session to do the reviews. There is no self-congratulation, but overly critical at times. Works well.

Honestly, sometimes the harnesses, specs, some predefined structure for skills etc all feel over-engineering. 99% of the time a bloody prompt will do. Claude Code is capable of planning, spawning sub-agents, writing tests and so on.

Claude.md file with general guidelines about our repo has worked extraordinarily good, without any external wrappers, harnesses or special prompts. Even the MD file has no specific structure, just instructions or notes in English.

New comment by throwaway7783 in "British Columbia is permanently adopting daylight time"

throwaway7783 — Mon, 02 Mar 2026 22:41:55 +0000

The article, however, says 93% wanted daylight savings in the linked public engagement report.

New comment by throwaway7783 in "How I use Claude Code: Separation of planning and execution"

throwaway7783 — Sun, 22 Feb 2026 06:05:32 +0000

I have to give this a try. My current model for backend is the same as how author does frontend iteration. My friend does the research-plan-edit-implement loop, and there is no real difference between the quality of what I do and what he does. But I do like this just for how it serves as documentation of the thought process across AI/human, and can be added to version control. Instead of humans reviewing PRs, perhaps humans can review the research/plan document.

On the PR review front, I give Claude the ticket number and the branch (or PR) and ask it to review for correctness, bugs and design consistency. The prompt is always roughly the same for every PR. It does a very good job there too.

Modelwise, Opus 4.6 is scary good!

New comment by throwaway7783 in "Breaking the spell of vibe coding"

throwaway7783 — Sun, 15 Feb 2026 05:23:16 +0000

Several, but I can't quite say it here. And I meant it for the codebase, not the person themselves

New comment by throwaway7783 in "Breaking the spell of vibe coding"

throwaway7783 — Sun, 15 Feb 2026 05:16:27 +0000

Everyone seems to have different ways to deal with AI for coding and have different experiences. But Armin's comment quoted in the article is spot on. I have seen a friend do exactly the same thing, vibe coded an entire product hooked to Cursor over three months. Filled with features no one uses, feeling very good about everything he built. Ultimately it's his time and money, but I would never want this in my company. While you can get very far with vibe coding, without the guiding hands and someone who understands what's really going on with the code, it ends up in a disaster.

I use AI for the mundane parts, for brainstorming bugs. It is actually more consistent than me in covering corner cases, making sure guard conditions exist etc. So I now focus more on design/architecture and what to build and not minutea.

New comment by throwaway7783 in "Software factories and the agentic moment"

throwaway7783 — Sun, 08 Feb 2026 02:33:28 +0000

This has happened to me too. Claude has stopped and said on occasions "this is a big refactor, and will affect UI as well. Do you want me to do it?"

New comment by throwaway7783 in "It's 2026, Just Use Postgres"

throwaway7783 — Thu, 05 Feb 2026 23:36:21 +0000

HA is not about exceeding the limits of a server. Its about still serving traffic when that best server I bought goes offline (or has failed memory chip, or a disk or... ).

New comment by throwaway7783 in "It's 2026, Just Use Postgres"

throwaway7783 — Thu, 05 Feb 2026 23:27:41 +0000

Can you please elaborate why?

New comment by throwaway7783 in "The TSA's New $45 Fee to Fly Without ID Is Illegal"

throwaway7783 — Tue, 03 Feb 2026 02:47:37 +0000

Ah, digging holes and refilling them - that'd be literally the NREGA program in India

New comment by throwaway7783 in "Waymo robotaxi hits a child near an elementary school in Santa Monica"

throwaway7783 — Fri, 30 Jan 2026 01:32:33 +0000

Same in India! We go one better, we let people drive in the opposite lane as well!