Hacker News: smy20011

New comment by smy20011 in "Don't post generated/AI-edited comments. HN is for conversation between humans."

smy20011 — Wed, 11 Mar 2026 19:55:39 +0000

At least easier to filter I think.

New comment by smy20011 in "Don't post generated/AI-edited comments. HN is for conversation between humans"

smy20011 — Wed, 11 Mar 2026 19:50:43 +0000

Agree, AI generated articles & comments provide little to none value other than the original prompt. Please just post the original prompt instead.

New comment by smy20011 in "Levels of Agentic Engineering"

smy20011 — Tue, 10 Mar 2026 18:13:25 +0000

I will not put it into a ladder. It implies that the higher the rank, the better. However, you want to choose the best solution for your needs.

New comment by smy20011 in "After outages, Amazon to make senior engineers sign off on AI-assisted changes"

smy20011 — Tue, 10 Mar 2026 16:53:43 +0000

An outage could cost Amazon ~millions to tens of millions. Most of the time, we want the junior to learn from the outage and fix the process. With AI agent, we can only update the agent.md and hope it will never happen again.

New comment by smy20011 in "Revealed: UK's multibillion AI drive is built on 'phantom investments'"

smy20011 — Mon, 09 Mar 2026 16:05:53 +0000

Just multibillion?

New comment by smy20011 in "SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via CI"

smy20011 — Sun, 08 Mar 2026 17:26:41 +0000

It interesting to see that the eval set becoming more and more expensive. Previously we just need to evaluate one test set, right now we need to create a lot of diffs and run a lot of tests.

New comment by smy20011 in "Show HN: Claude-replay – A video-like player for Claude Code sessions"

smy20011 — Fri, 06 Mar 2026 18:39:02 +0000

Nice to see a AI coding tool that not (complete) vibe coded! Well done.

New comment by smy20011 in "You need to rewrite your CLI for AI agents"

smy20011 — Thu, 05 Mar 2026 05:39:26 +0000

Are we reinventing RPC again? Calling CLI program with JSON sounds like RPC call. The schema feels likes something LSP can provided for such function.

Maybe asking agent to write/execute code that wraps CLI is a better solution.

New comment by smy20011 in "We tasked Opus 4.6 using agent teams to build a C Compiler"

smy20011 — Fri, 06 Feb 2026 07:08:31 +0000

I think the good thing about it is that if you are given good specification, you are likely to get good result. Writing a C compiler is not something new, but it will be great for all the porting projects.

New comment by smy20011 in "I miss thinking hard"

smy20011 — Wed, 04 Feb 2026 08:07:21 +0000

I miss entering flow state when coding. When vibe coding, you are in constant interruption and only think very shallow. I never see anyone enter flow state when vibe coding.

New comment by smy20011 in "How does misalignment scale with model intelligence and task complexity?"

smy20011 — Tue, 03 Feb 2026 01:16:07 +0000

I think It's not because AI working on "misaligned" goals. The user never specify the goal clearly enough for AI system to work.

However, I think producing detailed enough specification requires same or even larger amount of work than writing code. We write rough specification and clarify these during the process of coding. I think there are minimal effort required to produce these specification, AI will not help you speed up these effort.

New comment by smy20011 in "Eat Real Food"

smy20011 — Wed, 07 Jan 2026 22:15:09 +0000

According to https://cdn.realfood.gov/Daily%20Serving%20Sizes.pdf, their recommendations do not meet their calories goal. Eg, for 2000 calories, you can eat 4 egg, 3 cup of milk, 4 slice of bread, 2 apple and 3 tbsp of oil per day.

Total calories will be 1,608 kcal/day.

It's a very depressing diet menu.

New comment by smy20011 in "How to Keep Winning"

smy20011 — Fri, 07 Nov 2025 17:43:09 +0000

Just don't play the game have winner and loser. Play the game that both side can win.

The lawyer who beat Tesla is ready for 'round two'

smy20011 — Thu, 07 Aug 2025 21:10:04 +0000

Article URL: https://www.theverge.com/tesla/720157/tesla-death-lawsuit-verdict-lawyer-brett-schreiber-interview

Comments URL: https://news.ycombinator.com/item?id=44830404

Points: 22

# Comments: 2

Running Jujutsu with Claude Code Hooks

smy20011 — Tue, 15 Jul 2025 03:46:54 +0000

Article URL: https://matthewsanabria.dev/posts/running-jujutsu-with-claude-code-hooks/

Comments URL: https://news.ycombinator.com/item?id=44567664

Points: 3

# Comments: 0

New comment by smy20011 in "My AI skeptic friends are all nuts"

smy20011 — Mon, 02 Jun 2025 21:27:00 +0000

> Often, it will drop you precisely at that golden moment where shit almost works, and development means tweaking code and immediately seeing things work better. That dopamine hit is why I code.

Only if you are familiar with the project/code. If not, you were throw into a foreign codebase and have no idea how to tweak it.

New comment by smy20011 in "Tailscale is pretty useful"

smy20011 — Wed, 05 Mar 2025 22:08:01 +0000

Yeah, fully local LLM+TTS setup.

Use jupyter notebook to fetch the stock and weather info and feed that into a local LLM and convert that to speech using opensource TTS.

https://github.com/smy20011/MorningRadio

New comment by smy20011 in "Tailscale is pretty useful"

smy20011 — Wed, 05 Mar 2025 22:07:07 +0000

Local server.

https://github.com/smy20011/MorningRadio

Xiaomi Su7 has surpassed Tesla's Model 3 in China

smy20011 — Wed, 05 Mar 2025 20:51:45 +0000

Article URL: https://electrek.co/2025/03/05/this-chinese-ev-has-surpassed-teslas-model-3-and-model-y-is-next/

Comments URL: https://news.ycombinator.com/item?id=43272201

Points: 7

# Comments: 0

New comment by smy20011 in "Tailscale is pretty useful"

smy20011 — Wed, 05 Mar 2025 20:10:30 +0000

I use tailscale to build my personal podcast that include local weather and stocks I interested in. Running the whole pipeline on a steamdeck and use tailscale to securely delivery the generated podcast to my phone.