Hacker News: zora_goron

ChatGPT Available in CarPlay

zora_goron — Thu, 02 Apr 2026 17:19:32 +0000

Article URL: https://twitter.com/openai/status/2039748699350532097

Comments URL: https://news.ycombinator.com/item?id=47617283

Points: 3

# Comments: 0

Show HN: Museum Music

zora_goron — Thu, 05 Mar 2026 19:32:12 +0000

Museum Music is an app a friend and I built to enhance the museum experience with music. I had the habit of visiting museums with headphones in, but felt there was a disconnect between the works I was viewing and what I was listening to.

Museum Music lets you a picture of the exhibit you are viewing, identifies the period of the piece, and generates a contextually-appropriate Spotify soundtrack to accompany you.

It was originally built around two years ago, and LLM technology has considerably improved since then - so this felt like the perfect opportunity to test out coding agents by refactoring and improving the codebase!

Built using the GPT and Spotify APIs.

Comments URL: https://news.ycombinator.com/item?id=47266182

Points: 2

# Comments: 0

Physical Intelligence: scale brings alignment between human and robot data

zora_goron — Wed, 17 Dec 2025 16:59:26 +0000

Article URL: https://twitter.com/physical_int/status/2001096200456692114

Comments URL: https://news.ycombinator.com/item?id=46302099

Points: 1

# Comments: 0

New comment by zora_goron in "Claude Sonnet 4.5"

zora_goron — Mon, 29 Sep 2025 18:27:19 +0000

Why might this be, does anyone know?

Chrome DevTools MCP

zora_goron — Fri, 26 Sep 2025 18:50:16 +0000

Article URL: https://developer.chrome.com/blog/chrome-devtools-mcp

Comments URL: https://news.ycombinator.com/item?id=45389772

Points: 1

# Comments: 0

Claude Sonnet will ship in Xcode

zora_goron — Fri, 29 Aug 2025 00:44:27 +0000

Article URL: https://developer.apple.com/documentation/xcode-release-notes/xcode-26-release-notes

Comments URL: https://news.ycombinator.com/item?id=45058688

Points: 489

# Comments: 400

Augmenting clinical reasoning, without replacing it

zora_goron — Mon, 11 Aug 2025 22:11:56 +0000

Article URL: https://samrawal.substack.com/p/augmenting-clinical-reasoning-without

Comments URL: https://news.ycombinator.com/item?id=44870042

Points: 2

# Comments: 0

Claude Code Is All You Need

zora_goron — Mon, 14 Jul 2025 22:37:47 +0000

Article URL: https://twitter.com/trq212/status/1944877527044120655

Comments URL: https://news.ycombinator.com/item?id=44566113

Points: 4

# Comments: 0

New comment by zora_goron in "Clinical knowledge in LLMs does not translate to human interactions"

zora_goron — Sun, 15 Jun 2025 00:29:43 +0000

This difference between medical board examinations and real world practice is something that mirrors my real-world experience too, having finished med school and started residency a year ago.

I’ve heard others say before that real clinical education starts after medical school and once residency starts.

You can now connect GitHub repos to ChatGPT Deep Research

zora_goron — Fri, 09 May 2025 00:14:25 +0000

Article URL: https://twitter.com/openaidevs/status/1920556386083102844

Comments URL: https://news.ycombinator.com/item?id=43932624

Points: 2

# Comments: 0

New comment by zora_goron in "The Slow Collapse of Critical Thinking in OSINT Due to AI"

zora_goron — Fri, 04 Apr 2025 00:14:50 +0000

I wrote about some similar observations in the clinical domain -- I call it the "human -> AI reasoning shunt" [0]. Explicitly requesting an AI tool to perform reasoning is one thing, but a concern I have is that, with the increasing prevalence of these AI tools, even tasks that theoretically are not reasoning-based (ie helping write clinical notes or answer simple questions) can surreptitiously offload some degree of reasoning away from humans by allowing these systems to determine what bits of information are important or not.

[0] https://samrawal.substack.com/p/the-human-ai-reasoning-shunt

New comment by zora_goron in "Microsoft's new Dragon Copilot is an AI assistant for healthcare"

zora_goron — Tue, 04 Mar 2025 15:17:42 +0000

This doesn’t necessarily apply to this particular offering, but having working in clinical AI previously from a CS POV and currently from as a resident physician, something I’m a little wary of is the “shunting” of reasoning away from physicians to these tools (implicitly). One can argue that it’s not always a bad thing, but I think the danger can lie in this happening surreptitiously by these tools deciding what’s important and what’s not.

I wrote a little bit more of my thoughts here, in case it’s of interest to anyone: [0]

On that same vein, I recently made a tool I wrote for myself public [1] - it’s a “copilot” for writing medical notes that’s heavily focused on letting the clinician do the clinical reasoning, with the tool exclusively augmenting the flow rather than attempting to replace even a little bit of it.

[0] https://samrawal.substack.com/p/the-human-ai-reasoning-shunt

[1] https://x.com/samarthrawal/status/1894779710258733330

Deep research (ChatGPT) is now rolling out more widely

zora_goron — Tue, 25 Feb 2025 18:34:39 +0000

Article URL: https://twitter.com/openai/status/1894454194943529433

Comments URL: https://news.ycombinator.com/item?id=43175570

Points: 2

# Comments: 0

New comment by zora_goron in "Claude 3.7 Sonnet and Claude Code"

zora_goron — Tue, 25 Feb 2025 05:38:10 +0000

Does anyone know how this “user decides how much compute” is implemented architecturally? I assume it’s the same underlying model, so what factor pushes the model to for longer or shorter? Just a prompt-time modification or something else?

New comment by zora_goron in "OpenAI O3-Mini"

zora_goron — Sat, 01 Feb 2025 00:18:30 +0000

Does anyone know, how "reasoning effort" is implemented technically - does this involve differences in the pre-training, RL, or prompting phases (or all)?

New comment by zora_goron in "Discovery Coding"

zora_goron — Thu, 30 Jan 2025 00:32:42 +0000

“A programming language is for thinking of programs, not for expressing programs you’ve already thought of. It should be a pencil, not a pen.” - from PG’s “Hackers & Painters”

Contemplative LLMs

zora_goron — Sun, 12 Jan 2025 00:02:48 +0000

Article URL: https://maharshi.bearblog.dev/contemplative-llms-prompt/

Comments URL: https://news.ycombinator.com/item?id=42669985

Points: 26

# Comments: 10

The Human → AI Reasoning Shunt

zora_goron — Fri, 10 Jan 2025 18:41:08 +0000

Article URL: https://samrawal.substack.com/p/the-human-ai-reasoning-shunt

Comments URL: https://news.ycombinator.com/item?id=42658595

Points: 2

# Comments: 0

How I Use Claude

zora_goron — Thu, 02 Jan 2025 05:35:06 +0000

Article URL: https://borretti.me/article/how-i-use-claude

Comments URL: https://news.ycombinator.com/item?id=42571963

Points: 28

# Comments: 12

New comment by zora_goron in "Show HN: Semantic Macros Text Editor"

zora_goron — Mon, 21 Oct 2024 19:05:23 +0000

Thanks for trying it out! Honestly, no current idea of business model - this was just something I thought would be helpful in my daily workflow so I built it out.

The buttons are stored to localstorage, as is the editor text - everything stays locally (besides what is sent to the LLM). I'm planning on a simple import/export mechanism for transferring buttons across different browsers/computers!