Hacker News: makeramen

New comment by makeramen in "Chrome removes claim of On-device Al not sending data to Google Servers"

makeramen — Fri, 08 May 2026 02:26:42 +0000

Gemini is also the only major provider where you can't opt out of using your data for training without disabling chat history.

New comment by makeramen in "Banning All Anthropic Employees"

makeramen — Sat, 04 Apr 2026 23:36:50 +0000

You don’t think openai, google and other companies’ employees don’t do the same thing?

Of all the companies where employees are ghost-contributing llm code, Anthropic would be pretty low on my list to ban.

New comment by makeramen in "Drugwars for the TI-82/83/83 Calculators (2011)"

makeramen — Fri, 20 Mar 2026 04:37:38 +0000

Oh man, I ported this to the TI-89 back in 7th grade and made it slightly more school appropriate calling it “pop wars”, trading soda from different machines at different schools instead of drugs.

New comment by makeramen in "Shall I implement it? No"

makeramen — Fri, 13 Mar 2026 01:36:36 +0000

It will sometimes do this for gitignored files to avoid reading secret tokens in env files for example. But for certain languages that rely on code generation this can be a pain.

New comment by makeramen in "Ghostty – Terminal Emulator"

makeramen — Sun, 01 Mar 2026 21:04:24 +0000

Ah I just started using ghostty maybe a week ago and I mostly use quick terminal so I might be missing the panes on the regular windows.

New comment by makeramen in "Ghostty – Terminal Emulator"

makeramen — Sun, 01 Mar 2026 19:35:44 +0000

Zellij has been holding me over with tabs and panes (in quick terminal) while I wait for them to come to ghostty directly.

Tabs (and panes? I haven't tried yet) should work fine for regular terminal windows though.

New comment by makeramen in "OpenAI agrees with Dept. of War to deploy models in their classified network"

makeramen — Sat, 28 Feb 2026 07:18:55 +0000

The DoW wants to only be beholden to the laws, and not to Anthropics TOS.

So the question is: do you trust the government to effectively govern its own use of AI? or do you trust Anthropic's enforcement of its TOS?

New comment by makeramen in "The Robotic Dexterity Deadlock"

makeramen — Fri, 27 Feb 2026 20:28:18 +0000

I see it as trying to apply the bitter lesson to robotics. Specialized robots will always have their place, but humanoid ones can take advantage of all the design interfaces that already exist in the world for humans.

Similar to how claude code gained so much traction in terminal by just leveraging the command line interface that already exists for humans, no need to invent a domain specific MCP to just run shell commands.

I agree with you that it's far from the most efficient approach for specific tasks. But the analogy would be that you also generally don't want to use LLMs to do something you can "just" write a script for... that doesn't make LLMs useless though.

New comment by makeramen in "How I use Claude Code: Separation of planning and execution"

makeramen — Sun, 22 Feb 2026 07:11:14 +0000

Both can be true. I have personally experienced both.

Some problems AI surprised me immensely with fast, elegant efficient solutions and problem solving. I've also experienced AI doing totally absurd things that ended up taking multiple times longer than if I did it manually. Sometimes in the same project.

New comment by makeramen in "Android’s desktop interface leaks"

makeramen — Wed, 28 Jan 2026 21:09:47 +0000

> The fact that I can unlock and relock the bootloader is not a security issue or a risk. People who don't know what that means cannot possibly do it by mistake.

The second sentence is false. Lots of people blindly follow things and don't understand consequences until they brick their devices. Those who don’t break something won’t notice if they’ve silently backdoored themselves.

People asking for support after getting themselves into some weird hole they never should have been in because some friend or online article said so is super common.

New comment by makeramen in "LM Studio 0.4"

makeramen — Wed, 28 Jan 2026 20:27:08 +0000

Tailscale serve

A2UI: A Protocol for Agent-Driven Interfaces

makeramen — Tue, 16 Dec 2025 09:16:31 +0000

Article URL: https://a2ui.org/

Comments URL: https://news.ycombinator.com/item?id=46286407

Points: 164

# Comments: 75

New comment by makeramen in "Apple M5 chip"

makeramen — Wed, 15 Oct 2025 18:37:47 +0000

That seems like a typo or incorrect info, the M5 MBP definitely can be configured up to 32 GB, and the Apple page mentions 32 GB explicitly as well.

New comment by makeramen in "Auth.js is now part of Better Auth"

makeramen — Sat, 27 Sep 2025 00:16:20 +0000

You can probably infer some from their Ory case study: https://www.ory.sh/case-studies/openai

New comment by makeramen in "GPT-5: Key characteristics, pricing and system card"

makeramen — Thu, 07 Aug 2025 18:59:28 +0000

But given the option, do you choose bigger models or more reasoning? Or medium of both?

New comment by makeramen in "My experience with Claude Code after two weeks of adventures"

makeramen — Fri, 18 Jul 2025 04:06:58 +0000

You don't do it manually. You have claude do it once you’ve guided it back on track to remind itself not to do it next time.

New comment by makeramen in "Introducing Gemma 3n"

makeramen — Thu, 26 Jun 2025 18:13:05 +0000

Seems like that was a preview model, unknown if this released version is different

New comment by makeramen in "Swift 6"

makeramen — Tue, 17 Sep 2024 20:54:21 +0000

Kotlin Native's choice to go with a GC over native memory management is my biggest issue with it and really limits its use for memory and performance sensitive use cases.

New comment by makeramen in "Good programmers worry about data structures and their relationships"

makeramen — Fri, 16 Aug 2024 18:55:54 +0000

So basically [engineering] design is more important than implementation details.

I would say the "engineering" part of the design is also optional, as product design is also another lever of higher influence than code optimization.

New comment by makeramen in "Ask HN: What is the best code base you ever worked on?"

makeramen — Sat, 29 Jun 2024 06:46:28 +0000

That’s a recent development, used to be something else altogether.