HackerTrans
トップ新着トレンドコメント過去質問紹介求人

makeramen

2,463 カルマ登録 16 年前
Just a guy, doing some stuff.

投稿

ChatGPT Sites

help.openai.com
3 ポイント·投稿者 makeramen·一昨日·0 コメント

WSL Container – Linux Containers on Windows

learn.microsoft.com
2 ポイント·投稿者 makeramen·13 日前·0 コメント

A2UI: A Protocol for Agent-Driven Interfaces

a2ui.org
164 ポイント·投稿者 makeramen·7 か月前·75 コメント

コメント

makeramen
·2 か月前·議論
Gemini is also the only major provider where you can't opt out of using your data for training without disabling chat history.
makeramen
·3 か月前·議論
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.
makeramen
·4 か月前·議論
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.
makeramen
·4 か月前·議論
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.
makeramen
·4 か月前·議論
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.
makeramen
·4 か月前·議論
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.
makeramen
·4 か月前·議論
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?
makeramen
·4 か月前·議論
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.
makeramen
·5 か月前·議論
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.
makeramen
·5 か月前·議論
> 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.
makeramen
·5 か月前·議論
Tailscale serve
makeramen
·9 か月前·議論
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.
makeramen
·10 か月前·議論
You can probably infer some from their Ory case study: https://www.ory.sh/case-studies/openai