Hacker News Reader

s900mhzon Goodbye Google

I don’t think that’s what he meant. They both are surveillance tools. He’s just upset only one of those is making people advertise their leave in protest.

s900mhzon iOS 27, iPadOS 27, and macOS 27

This is the case for me too. If I try to automate sign in, it trips bot detection. But if I manually sign in then let the agent rip, I'm fine.

s900mhzon OpenAI’s Navier-Stokes release included a Lean 4 formal proof

IMO It’s not about being trained on the data, it’s more like what do the agents have access to during inference? Can they grep customer transcripts/logs?

s900mhzon Grok Bot

I agree, but I made myself laugh pondering a solution to this in which I came up with a Raspberry Pi like device that acts as the loopback for the agent. Always keep it on and plugged in.

I would like to introduce the Grok Box

s900mhzon New Amazon Data Center Is Set to Have the Most Polluting Power Plant in the U.S.

No one mentioned communism?

s900mhzon Ask HN: What are you working on? (June 2026)

I have a similar setup at home, I’m sure you heard this before but I must +1 the Infuse app on Apple devices. It’s a much better client than Jellyfin’s but can connect to Jellyfin server no problem. No plex needed.

s900mhzon Open Code Review – An AI-powered code review CLI tool

Yes! Where it gets really interesting is the scenario in which every developer has their own unique review skill/workflow, so the reviews end up being different than you running it yourself, but nobody is reading them still.

s900mhzon Cartoon Network Flash Games

Thank you!

s900mhzon Cartoon Network Flash Games

This is awesome!

I hope they can restore the cartoon cartoon summer resort games.

s900mhzon GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

Has 5.1 reliability improved? I would love to use it again. The inference was just too unreliable when it was first released.

s900mhzon Anatomy of the .claude/ folder

Yes this is the path I’m taking. Experiment, build your own toolbox whether it’s hand rolled skills or particular skills you pull out from other public repos. Then maintain your own set.

You do not want to log in one day to find your favorite workflow has changed via updates.

Then again this is all personal preference as well.

s900mhzon Show HN: Lux – Drop-in Redis replacement in Rust. 5.6x faster, ~1MB Docker image

Looks like the repo is very young.

First thing to do is try it out in a hobby project see how it works out!

s900mhzon 1M context is now generally available for Opus 4.6 and Sonnet 4.6

I find it useful to make Claude track the debugging session with a markdown file. It’s like a persistent memory for a long session over many context windows.

Or make a subagent do the debugging and let the main agent orchestrate it over many subagent sessions.

s900mhzon Claude Code On-the-Go

I was doing the same, but recently I noticed that Claude now writes its plans to a markdown file somewhere nested in the ~/.claude/plans directory. It will carry a reference to it through compaction. Basically mimicking my own workflow!

This can be customized via a shell env variable that I cannot remember ATM.

The downside (upside?) is that the plan will not end up in your repo. Which sometimes I want. I love the native plan mode though.

s900mhzon One year of keeping a tada list

Why not? If one of your goals is to try to relax and/or meditate more, then I feel it’s a valid list entry.

It’s all a matter of perspective and personal goals, no?

s900mhzon Claude in Chrome

I personally replaced my playwright mcp with this. Seems to use less context and generally more reliable.

s900mhzon Claude Advanced Tool Use

This is a task I think is suited for a sub agent that is small in size. It can can take the context beating to query for relevant tools and return only what is necessary to the main agent thread.

s900mhzon Study identifies weaknesses in how AI systems are evaluated

When I have a bug I’m iterating on it’s much easier and faster to have it write out the playwright script. That way it does not have to waste time or tokens performing the same actions over and over again.

Think of it as TDD.

s900mhzon Claude Skills

Download the godot docs and tell the skill to use them. It won’t be able to fit the entire docs in the context but that’s not the point. Depending on the task it will search for what it needs

s900mhzon Claude Sonnet 4.5

I personally do not do any writes in parallel but parallel works great for read operations like investigating multiple failing tests.

s900mhzon Unix philosophy and filesystem access makes Claude Code amazing

Claude can then proceed to fix the issues for you

s900mhzon Claude Sonnet 4.5

You can use the built in task agent. When you have a plan and ready for Claude to implement, just say something along the line of “begin implementation, split each step into their own subagent, run them sequentially”

s900mhzon Devious malware has jumped from Meta to Google Ads and YouTube to spread

https://apps.apple.com/us/app/wipr-2/id1662217862

Wipr 2

It’s a one time paid app that works for both Mac and iOS

s900mhzon AI overviews cause massive drop in search clicks

Ahh thanks for the clarification, I misunderstood!

s900mhzon AI overviews cause massive drop in search clicks

It’s a feature of Kagi. Putting the question mark does invoke AI summaries.

https://help.kagi.com/kagi/ai/quick-answer.html

s900mhzon What happens when people don't understand how AI works

I personally love LLMs and use them daily for a variety of tasks. I really do not know how to “fix” the terminology. I agree with you that they are not thinking in the abstract like humans. I also do not know what else you would call “chain-of-thought”.

Perhaps “journaling-before-answering” lol. It’s basically talking out loud to itself. (Is that still being too anthropomorphic?)

Is this comment me “thinking out loud”? shrug

s900mhzon Tracking Copilot vs. Codex vs. Cursor vs. Devin PR Performance

I use Claude code daily at work, it writes all my PRs. It uses the GitHub cli to manage them.

Since all agents are able to use the terminal I suggest looking up the Gitlab CLI and have it use that. Should work locally and in runners.

s900mhzon Cloudlflare builds OAuth with Claude and publishes all the prompts

I’m not who you replied to but I keep functions small and testable paired with unit tests with a healthy mix of happy/sad path.

Afterwards I make sure the LLM passes all the tests before I spend my time to review the code.

I find this process keeps the iterations count low for review -> prompt -> review.

I personally love writing code with an LLM. I’m a sloppy typist but love programming. I find it’s a great burnout prevention.

For context: node.js development/React (a very LLM friendly stack.)

s900mhzon xAI to pay telegram $300M to integrate Grok into the chat app

Perplexity basically has this right? They let you buy things with a button in the chat itself!

s900mhzon MCP explained without hype or fluff

You can, most MCP servers are just wrappers around existing SDKs or even rest endpoints.

I think it all comes down to discovery. MCP has a lot of natural language written in each of its “calls” allowing the LLM to understand context.

MCP is also not stateless, but to keep it short. I believe it’s just a way to make these tools more discoverable for the LLM. MCP doesn’t do much that you can’t with other options. Just makes it easier on the LLM.

That’s my take as someone who wrote a few.

Edit: I like to think of them as RCP for LLM