Hacker News Reader

meander_wateron Show HN: I built a frontpage for personal blogs

Cool idea! I actually did something similar but with ~130k Substack publications (they're just RSS feeds) https://findsubstack.com

meander_wateron Claude Code runs Git reset –hard origin/main against project repo every 10 mins

Probably does it to reduce context for regex/git history searches

meander_wateron Show HN: I replaced Substack's algorithm with a chronological feed of new posts

Thanks for checking it out!

meander_wateron Thinking Fast, Slow, and Artificial: How AI Is Reshaping Human Reasoning

I'm conflicted about this. As I was reading the paper, my AI detector senses were tingling all over the place.

Large parts of the paper score very high probability of being written entirely by AI in gptzero.

I'm not sure if I could trust anything written in it.

meander_wateron Building a Procedural Hex Map with Wave Function Collapse

This is an amazing resource, thanks for sharing

meander_wateron Show HN: If you lose your memory, how to regain access to your computer?

Seems similar to a Show HN from 5 years ago: https://news.ycombinator.com/item?id=26256726

I gotta say Horcrux is a catchier name ;)

meander_wateron Dead Internet Theory

Yeah that's been my experience as well. I think most uploads strip the metadata unfortunately

meander_wateron The Code-Only Agent

Have you done a comparison on token usage + cost? I'd imagine there would be some level of re-inventing the wheel (i.e. rewriting code for very similar tasks) for common tasks, or do you re-use previously generated code?

meander_wateron Dead Internet Theory

Not foolproof, but a couple of easy ways to verify if images were AI generated:

- OpenAI uses the C2PA standard [0] to add provenance metadata to images, which you can check [1]

- Gemini uses SynthId [2] and adds a watermark to the image. The watermark can be removed, but SynthId cannot as it is part of the image. SynthId is used to watermark text as well, and code is open-source [3]

[0] https://help.openai.com/en/articles/8912793-c2pa-in-chatgpt-...

[1] https://verify.contentauthenticity.org/

[2] https://deepmind.google/models/synthid/

[3] https://github.com/google-deepmind/synthid-text

meander_wateron Scaling long-running autonomous coding

The lowest bar in agentic coding is the ability to create something which compiles successfully. Then something which runs successfully in the happy path. Then something which handles all the obvious edge cases.

By far the most useful metric is to have a live system running for a year with widespread usage that produces a lower number of bugs than that of a codebase created by humans.

Until that happens, my skeptic hat will remain firmly on my head.

meander_wateron Bubblewrap: A nimble way to prevent agents from accessing your .env files

I recently created a throwaway API key for cloudflare and asked a cursor cloud agent to deploy some infra using it, but it responded with this:

> I can’t take that token and run Cloudflare provisioning on your behalf, even if it’s “only” set as an env var (it’s still a secret credential and you’ve shared it in chat). Please revoke/rotate it immediately in Cloudflare.

So clearly they've put some sort of prompt guard in place. I wonder how easy it would be to circumvent it.

meander_wateron I switched from VSCode to Zed

For those looking for a better language server for python, I would recommend ruff. As of v0.4.5 it's completely written in rust, and much faster than pylance.

If you've got the ruff plugin installed it should use it by default. Should be able to use it in zed as well.

meander_wateron Show HN: 22 GB of Hacker News in SQLite

Hah, well that's embarrassing

meander_wateron Show HN: 22 GB of Hacker News in SQLite

I love this so much, on my phone this is much faster than actual HN (I know it's only a read-only version).

Where did you get the 22GB figure from? On the site it says:

> 46,399,072 items, 1,637 shards, 8.5GB, spanning Oct 9, 2006 to Dec 28, 2025

meander_wateron Go away Python

Actually you can go one better:

  #!/usr/bin/env -S uv run --python 3.14 --script

Then you don't even need python installed. uv will install the version of python you specified and run the command.

meander_wateron ManusAI Joins Meta

I'd like someone to do a comparison of tech company valuations pre GenAI vs post for the same vertical.

I understand there's always some optimism for new tech, but the valuations we're seeing seems absurd to me.

Like, do they expect to see x100 profit for the same vertical? Obviously some new markets have been created, but I don't see them solving any particularly novel business problems.

meander_wateron Show HN: Minimalist editor that lives in browser, stores everything in the URL

Cool project, but loading "Crime and Punishment" crashed my mobile browser.

I don't think urls were built for that kind of punishment.

meander_wateron Microsoft please get your tab to autocomplete shit together

This is actually bearable compared to the new terminal suggestions in vscode. Not only does it autosuggest bizzare completions for commands, it breaks shell completions. So when I tab a file path, it shoves the absolute path into the partially typed path making it unusable.

meander_wateron Slowness is a virtue

Oh interesting, can you share any links or books?

meander_wateron Slowness is a virtue

For anyone interested in the history of IQ tests and how broken they are check out The Mismeasure of Man [0]

[0] https://en.wikipedia.org/wiki/The_Mismeasure_of_Man

meander_wateron Working quickly is more important than it seems (2015)

One could argue that learned speed has the hours of practice "baked in" so it's actually much slower. And that's not a bad thing IMO.

I think this post only covers one side of the coin. Sure, getting things done fast achieves the outcome, but in the long run you retain and learn less. Learning new stuff takes time and effort.

meander_wateron A2UI: A Protocol for Agent-Driven Interfaces

This provides a bit more detail on how they relate to each other

https://www.copilotkit.ai/ag-ui-and-a2ui

meander_wateron State of AI: An Empirical 100T Token Study with OpenRouter

Overall really interesting read, but I'm having trouble processing this:

> OpenRouter performs internal categorization on a random sample comprising approximately 0.25% of all prompts

How can you arrive at any conclusion with such a small random sample size?

meander_wateron Anti-patterns while working with LLMs

Yeah I was hoping for a lot more from the title.

meander_wateron Show HN: Runprompt – run .prompt files from the command line

This is really cool and interesting timing, as I created something similar recently - https://github.com/julio-mcdulio/pmp

I've been using mlflow to store my prompts, but wanted something lightweight on the cli to version and manage prompts. I setup pmp so you can have different storage backends (file, sqlite, mlflow etc.).

I wasn't aware of dotprompt, I might build that in too.

meander_wateron MCP Apps: Extending servers with interactive user interfaces

We already have AG-UI [0], which has been implemented by frameworks like Microsoft agent framework, pydantic AI and llamaindex. I guess they'll just have to duplicate functionality.

Sigh.

[0] https://docs.ag-ui.com/introduction

meander_wateron Show HN: I built a wizard to turn ideas into AI coding agent-ready specs

I've been doing something like this for a while, and it provides decent enough results for agents to one-shot. The key is to specify the LLM with the idea, and then get it to ask you questions until you feel enough ambiguity has been eliminated from the product spec for you to pass it to an agent.

meander_wateron WorldGen – Text to Immersive 3D Worlds

It's funny, I clicked the link to the demo, but it 404s, then I tried googling Worldgen, and it turns out someone else has built the same thing in May and called it Worldgen as well. Looks like it does better at realistic 3D scenes compared to this.

[0] https://worldgen.github.io/index.html