throwaway7783

The article mixes transaction semantics (distributed or otherwise) with idempotency.

Idempotency or not, many points in the articles are are about atomic transactions.

By that logic, all "injustice" is "I don't like it when X happens" - there is nothing more.

Wow, I contracted in Jamnagar for Reliance building software back in 1999-2000. It was fun building a web interface to report on their IoT (not called IoT back then) devices - sensors, meters and whatnots through a CORBA/C++ interface. That was very advanced for those days.

Re: AI slop - What does this mean in practice? Better "system" prompts?

This is not true in my experience at all. I never write such detailed spec for AI - and that is my value as the human in the loop - to be iterative, to steer and make decisions. The AI in fact catches more edge cases than I do, and can point me to things that I never considered myself. Our productivity has increased manyfold, and code quality has increased significantly because writing tests is no longer a chore or an afterthought, or the biggest one for us - "test setup is too complicated". All of that is gone. And it is showing in a decrease in customer reported issues

I don't know. I don't write detailed specs, but make it very iterative, with two sessions. One for coding and one for reviews at various levels.

Just the coding window makes mistakes, duplicates code, does not follow the patterns. The reviewer catches most of this, and the coder fixes them all after rationalizing them.

Works pretty well for me. This model is somewhat institutionalized in my company as well.

I use CC Opus 4.7 or Codex GPT 5.4 High (more and more codex off late).

Yeah. We also use gitlab instead of github. I'll check this out later. We also have set it up to work with multiple repos to truly understand context (we have frontend, backend, some tooling etc, an MCP server etc all in different repos).

Cool! We have a similar setup,connected to JIRA, but it stops at analysis and approach to solution. I'm taking inspiration from this now to take it to the next level!

Yes. Even without Claude design and just Claude code, it can use existing design and build out new mockups in-app, which is much easier to demo , tweak and then implement the backend (if any) - all through Claude Code (or Codex if you prefer that). We use both and are now leaning more towards Codex over Claude

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

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

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.

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.

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

Does House of Lords have any real power today?

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

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

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

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.

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.

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

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!

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

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.

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?"

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... ).

Can you please elaborate why?

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

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

Funny how San Francisco can't fit the chart they have. League of its own I guess.