Hacker News: ZitchDog

New comment by ZitchDog in "Can we have the day off?"

ZitchDog — Thu, 28 May 2026 00:52:26 +0000

Shoot, I'd be happy with free health care.

New comment by ZitchDog in "Claude Code Routines"

ZitchDog — Wed, 15 Apr 2026 15:11:44 +0000

This is the new challenge. Every vibecoder is larping as a SWE and rewriting systems left and right when all they need is a new feature or two. 6000 line PRs that could be 60. The challenge in the current era is evolving existing systems to ensure they meet previous requirements in terms of capabilities and performance. This is the new role of the SWE. Same as the old role, but with less typing.

New comment by ZitchDog in "Functional programming accelerates agentic feature development"

ZitchDog — Sun, 05 Apr 2026 18:50:13 +0000

Can't fully enforce that one, but I require only my specific HTTP router / SQL library to be used, and disallow the import of express / pg libraries via eslint. I also disable the use of JSON.parse via eslint. Combined with strong language in the CLAUDE.md, I haven't seen it get around my guard rails.

New comment by ZitchDog in "Functional programming accelerates agentic feature development"

ZitchDog — Sun, 05 Apr 2026 04:23:05 +0000

I've been having good luck with fairly autonomous LLM coding with the following rules:

  * TypeScript everywhere with extreme enforcement of the type system.

  * No "as" casts, no "any" declarations, all code must understand the shape of its data

  * All boundaries validated using a typed validation library. Many use zod, I prefer tjs. I also have strictly typed pg and express wrappers.

  * No files longer than 300 lines

  * All of these rules are enforced by an eslint configuration that runs in a pre commit hook.

Global state and classes could also be removed via eslint rules, that would be interesting, though I haven't found it to be an issue in practice once the types are strictly enforced.

New comment by ZitchDog in "SpaceX files to go public"

ZitchDog — Wed, 01 Apr 2026 23:58:44 +0000

You can’t trade options on an IPO.

New comment by ZitchDog in "How the AI Bubble Bursts"

ZitchDog — Mon, 30 Mar 2026 14:06:04 +0000

> they have no incentive to do this at a loss

Are you sure? Surely there is a lot of interesting data in those LLM interactions.

New comment by ZitchDog in "Don't become an engineering manager"

ZitchDog — Tue, 03 Mar 2026 14:50:33 +0000

Saying that becoming an EM is "moving away from tech" is crazy. As an EM you will be steeped in tech, just as you would be as an IC. It just may not be the tech you want to be steeped in. Again, same as an IC. In either case, unless you are working in AI, you will need to "play" with things like OpenClaw in your spare time.

The real reason not to become an EM in 2026 is because AI makes our jobs 10x harder.

New comment by ZitchDog in "Claws are now a new layer on top of LLM agents"

ZitchDog — Fri, 27 Feb 2026 23:18:34 +0000

I haven't needed that yet! But it seems like the agent could easily be notified of completed activities.

New comment by ZitchDog in "Claws are now a new layer on top of LLM agents"

ZitchDog — Fri, 27 Feb 2026 23:17:38 +0000

Nope! The summary is presented to the user via a link and once the user follows the link and approves, the action is implemented entirely outside of the agent, on a separate server.

New comment by ZitchDog in "Claws are now a new layer on top of LLM agents"

ZitchDog — Sat, 21 Feb 2026 19:33:27 +0000

I've created my own "claw" running in fly.io with a pattern that seems to work well. I have MCP tools for actions that I want to ensure human-in-the loop - email sending, slack message sending, etc. I call these "activities". The only way for my claw to execute these commands is to create an activity which generates a link with the summary of the acitvity for me to approve.

New comment by ZitchDog in "Ask HN: Do you have any evidence that agentic coding works?"

ZitchDog — Wed, 21 Jan 2026 21:25:09 +0000

Here are benchmark results vs AJV: https://github.com/sberan/tjs/blob/main/benchmarks/results/B...

There are raw stats in the main graph image of the readme (op/s)

I don't compare it to that validator because these are JS only - I'll update to specify the language preference. Thanks for the feedback.

New comment by ZitchDog in "Ask HN: Do you have any evidence that agentic coding works?"

ZitchDog — Wed, 21 Jan 2026 15:40:32 +0000

I had the same question recently! So I did an experiment to see if I could create something of value using agentic coding.

I made the worlds fastest and most accurate JSON Schema parser.

https://github.com/sberan/tjs

But, nobody seems to care. The repo only has 18 stars and my Show HN post got no upvotes. I'm not sure what to take away from that.

New comment by ZitchDog in "Ask HN: Do you have any evidence that agentic coding works?"

ZitchDog — Wed, 21 Jan 2026 15:38:20 +0000

> In the domains where I'm an expert, it's a nice productivity boost. In the domains where I'm not, it's transformative.

Is it possible that the code you are writing isn't good, but you don't know it because you're not an expert?

New comment by ZitchDog in "Ask HN: Do you have any evidence that agentic coding works?"

ZitchDog — Wed, 21 Jan 2026 15:34:22 +0000

I had the same question recently! So I did an experiment to see if I could create something of value using agentic coding.

I made the worlds fastest and most accurate JSON Schema validator.

https://github.com/sberan/tjs

New comment by ZitchDog in "Show HN: TJS, The World's Fastest and Most Accurate JSON Schema Validator"

ZitchDog — Mon, 19 Jan 2026 15:21:44 +0000

Hi HN!

I built TJS over my holiday as a way to experiment and get better at agentic coding. I was astounded at how quickly software can be built when you have a full test spec like JSON Schema has.

The thing I'm most proud of is the TypeScript type inference. It automatically deduces the types from the JSON Schema. Try it out in the playground to see what I mean! https://sberan.github.io/tjs/#playground

Show HN: TJS, The World's Fastest and Most Accurate JSON Schema Validator

ZitchDog — Mon, 19 Jan 2026 15:18:02 +0000

Article URL: https://github.com/sberan/tjs

Comments URL: https://news.ycombinator.com/item?id=46679931

Points: 1

# Comments: 1

New comment by ZitchDog in "Scaling long-running autonomous coding"

ZitchDog — Wed, 14 Jan 2026 22:41:54 +0000

I used similar techniques to build tjs [1] - the worlds fastest and most accurate json schema validator, with magical TypeScript types. I learned a lot about autonomous programming. I found a similar "planner/delegate" pattern to work really well, with the use of git subtrees to fan out work [2].

I think any large piece of software with well established standards and test suites will be able to be quickly rewritten and optimized by coding agents.

[1] https://github.com/sberan/tjs

[2] /spawn-perf-agents claude command: https://github.com/sberan/tjs/blob/main/.claude/commands/spa...

New comment by ZitchDog in "Unexpected things that are people"

ZitchDog — Mon, 10 Nov 2025 23:49:30 +0000

Not correct: A share is a contract issued by the corporation entitling its owner to a share of future profits. So you're not buying a corporation, just engaging in a contract with it.

I hate Citizens United as much as the next guy, but this isn't a good argument against it.

New comment by ZitchDog in "[dead]"

ZitchDog — Fri, 16 May 2025 14:56:03 +0000

I used to think prayer was really dumb too, but then I started practicing Metta meditation created by Buddhists, and I realized it's very similar to Christian prayer. The power of Metta and prayer is actually the change it makes in the one praying. Wishing well for others improves one's whole outlook and posture in the world.

The "official" way to pray outlined in the Lord's prayer isn't selfish (other than asking to have enough food to get through the day), and is asking for redemption / forgiveness rather than specific goodies. This is the right way to do it.

New comment by ZitchDog in "Show HN: Zero-codegen, no-compile TypeScript type inference from Protobufs"

ZitchDog — Mon, 14 Apr 2025 19:39:02 +0000

The problem is that TypeScript is terrible at codegen, there are no standard extension points like we have with javac and others. So we are forced to do these crazy hacks at the type level rather than just generating types as you would in other languages.