ZitchDog

How do you make sure they aren’t using AI to pretend to be a domain expert? I’d think an AI would be pretty good at that.

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

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.

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.

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.

You can’t trade options on an IPO.

> 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.

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.

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

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.

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.

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.

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.

> 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?

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

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

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...

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.

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.

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.

This is what happened to me in middle school. I wrote a bunch of programs to “help” me with algebra II tests and ended up inadvertently learning an insanely marketable skill in the process.

It's not just people who gave them data who should be worried. If a close relative gave their info to 23andme, they probably have enough data to associate your DNA with that relative. For instance my mom did 23andme and now 50% of my DNA is in this private commercial database without my consent and this data is completely unencumbered by HIPAA privacy restrictions.

Cool!! Is this available outside of pglite or does it require it for some reason? I could see this being very widely useful.

> it has a reactive "live query" API

Very cool! Most of the examples for reactive queries are very basic (only single tables). Do live queries support joins / aggregations?

I am halfway through this book and wanting to read it slower because it's that good. I think we could make a pretty cool AI powered ARG based on the lore.

Yes please be careful here folks. Nicotine can also cause anxiety and panic attacks.

Htmx doesn't help with this problem (knowing whether the underlying data has changed in order to update the UI). It's a common problem in any kind of collaborative app.

One thing that postgres does not solve very well is reactive UIs. Postgres does have listen/notify but it requires much more boilerplate and infrastructure to set up than Firebase/Firestore. For example I'd like to be able to run a query and get notified that the results have updated when any of the affected rows change.

I would much rather inherit and optimize someone's postgres DB with specific scaling challenges than a prematurely optimized multi-database solution built for "web scale".

I think this is quite different- I don’t think mojo runs on the GPU unless I am mistaken.