Hacker News: joshuastuden

New comment by joshuastuden in "Eight Myths on Software Engineering and GenAI"

joshuastuden — Wed, 05 Aug 2026 02:48:36 +0000

Exactly. I saw them using things from 2025... AI sorta sucked then and didn't really "take off" until that Opus drop in December or whatever it was.

New comment by joshuastuden in "Zuckerberg says AI agent development going slower than expected"

joshuastuden — Sun, 05 Jul 2026 18:39:08 +0000

That seems to be because Apple's AI division sucks. OpenAI came in 2018 and chatGPT 2.0 was already way better than anything Apple ever did.

New comment by joshuastuden in "Emacs 31 is around the corner: The changes I'm daily driving"

joshuastuden — Fri, 19 Jun 2026 05:04:31 +0000

Agent-shell.el for the CLI experience that's integrated with emacs. You can send things from emacs to your Claude code prompt and it will include the file and line numbers.

There's also claude-code-ide.el that gives you more of a cursor like experience with autocomplete, simple chat, etc.

New comment by joshuastuden in "Emacs 31 is around the corner: The changes I'm daily driving"

joshuastuden — Fri, 19 Jun 2026 05:01:25 +0000

Agent-shell.el and claude-code-ide.el

Agent-shell is like the Claude code CLI. Claude-code-ide is like cursor with ghost completions/auto complete, chat, etc.

New comment by joshuastuden in "Emacs 31 is around the corner: The changes I'm daily driving"

joshuastuden — Fri, 19 Jun 2026 04:58:27 +0000

Emacs can give you all the vim key bindings. Vim can't do that.

New comment by joshuastuden in "Emacs 31 is around the corner: The changes I'm daily driving"

joshuastuden — Fri, 19 Jun 2026 04:55:57 +0000

Yes to some extent. When you attach to it, the default screen will still be scratch, but all your buffers are still open. There are some settings you can set to fix that, if it's burdensome.

New comment by joshuastuden in "Emacs 31 is around the corner: The changes I'm daily driving"

joshuastuden — Fri, 19 Jun 2026 04:54:33 +0000

Emacs --daemon once and then attach to it with emacsclient.

New comment by joshuastuden in "Emacs 31 is around the corner: The changes I'm daily driving"

joshuastuden — Fri, 19 Jun 2026 04:52:52 +0000

I don't understand what this means. How does claude-code-ide support or need a terminal like ghostel?

New comment by joshuastuden in "Emacs 31 is around the corner: The changes I'm daily driving"

joshuastuden — Fri, 19 Jun 2026 02:28:40 +0000

Also, if a slash command is missing, that's because the model's ACP client doesn't implement it:

https://github.com/xenodium/agent-shell#why-doesnt-agent-she...

New comment by joshuastuden in "Emacs 31 is around the corner: The changes I'm daily driving"

joshuastuden — Fri, 19 Jun 2026 02:28:09 +0000

C-c C-v to change the model or M-x agent-shell-set-session-model

New comment by joshuastuden in "Emacs 31 is around the corner: The changes I'm daily driving"

joshuastuden — Thu, 18 Jun 2026 23:29:11 +0000

When on the agent shell buffer, do C-c C-v with the latest agent-shell to change the model

New comment by joshuastuden in "Emacs 31 is around the corner: The changes I'm daily driving"

joshuastuden — Thu, 18 Jun 2026 23:24:27 +0000

Anthropic scrapped their sdk billing thing

New comment by joshuastuden in "Emacs 31 is around the corner: The changes I'm daily driving"

joshuastuden — Thu, 18 Jun 2026 14:54:16 +0000

Emacs evil-mode gives you vim bindings.

New comment by joshuastuden in "Emacs 31 is around the corner: The changes I'm daily driving"

joshuastuden — Thu, 18 Jun 2026 14:22:05 +0000

Why not use agent-shell? It makes the whole experience great.

Also claude-code-ide.el. try these

New comment by joshuastuden in "OpenAI Losses Increased Nearly 8X in 2025, with Spending Hitting $34B"

joshuastuden — Thu, 18 Jun 2026 02:59:28 +0000

GPT 5.5 regularly got things correct where opus 4.8 got things wrong. Just today, it was launching an executable and putting the environments after the launch. It should have been

Env1=val env2=val ./executable ....

But instead it did

./executable

Then set the envvars. Chatgpt 5.5 made no such mistake.

New comment by joshuastuden in "OpenAI Losses Increased Nearly 8X in 2025, with Spending Hitting $34B"

joshuastuden — Thu, 18 Jun 2026 02:57:14 +0000

>The projections, which were reviewed by The Wall Street Journal

No, they're just projections of profitability

New comment by joshuastuden in "OpenAI Losses Increased Nearly 8X in 2025, with Spending Hitting $34B"

joshuastuden — Thu, 18 Jun 2026 02:56:04 +0000

Did you read it? It just said AI assisted with the process. So did the Internet. AI didn't come up with the solution or even the idea. It simply helped prune the search space, which is valuable, but not worth the trillions of dollars invested and all the added CO2.

New comment by joshuastuden in "OpenAI Losses Increased Nearly 8X in 2025, with Spending Hitting $34B"

joshuastuden — Thu, 18 Jun 2026 01:10:02 +0000

They already fold proteins with simulations.

Just because people are using it doesn't mean it's a net good. Lots of people use social media and that's just rotting brains and making people far more polarized than they ever were before.

It's use in medicine hasn't resulted in anything meaningful. Nobody's medical bill has gotten cheaper and nobody has lived longer or healthier because of anything AI did.

New comment by joshuastuden in "OpenAI Losses Increased Nearly 8X in 2025, with Spending Hitting $34B"

joshuastuden — Thu, 18 Jun 2026 00:45:00 +0000

They haven't done humanity a favor at all. The innovation that these LLMs have produced has been small. A few fun math theorems where the answer was gleaned from a pattern in the training data. Great,.but it doesn't change the world one bit.

That latest drug for pancreatic cancer? Yeah, all human. After the trillions already spent, AI hasn't come up with any new medications, no new inventions to save lives... Nothing

New comment by joshuastuden in "Leaked financial docs show OpenAI is losing billions of dollars a year"

joshuastuden — Thu, 18 Jun 2026 00:41:46 +0000

They're not really losing ground to Anthropic. 5.5 was a bit better than 4.8. Fable was good, and was a jump over 4.8, but only incremental over 5.5.

Anthropic is also likely losing money, right?