HNHacker News
TopNewBestAskShowJobs

smy20011

415 karma · joined May 26, 2016

submissionscomments
smy20011··on There Is Life Before Main in Rust
> This post is 100% human-written. Claude was used for feedback and to assist with the linker symbol diagram. Cursor was used for feedback and to ensure examples were compilable.

Love this, I hope every blog have the same disclaimer about how AI is used.

smy20011··on Waymo Premier
It will pay for itself if you spend >300$ per month. I personally wish Waymo have a 399$ per month subscription that give 2 free ride per day so I don't need to own a car just for work.
smy20011··on Don't post generated/AI-edited comments. HN is for conversation between humans.
At least easier to filter I think.
smy20011··on Don't post generated/AI-edited comments. HN is for conversation between humans
Agree, AI generated articles & comments provide little to none value other than the original prompt. Please just post the original prompt instead.
smy20011··on Levels of Agentic Engineering
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.
smy20011··on After outages, Amazon to make senior engineers sign off on AI-assisted changes
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.
smy20011··on Revealed: UK's multibillion AI drive is built on 'phantom investments'
Just multibillion?
smy20011··on SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via CI
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.
smy20011··on Show HN: Claude-replay – A video-like player for Claude Code sessions
Nice to see a AI coding tool that not (complete) vibe coded! Well done.
smy20011··on You need to rewrite your CLI for AI agents
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.

smy20011··on We tasked Opus 4.6 using agent teams to build a C Compiler
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.
smy20011··on I miss thinking hard
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.
smy20011··on How does misalignment scale with model intelligence and task complexity?
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.

smy20011··on Eat Real Food
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.

smy20011··on How to Keep Winning
Just don't play the game have winner and loser. Play the game that both side can win.
smy20011··on My AI skeptic friends are all nuts
> 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.

smy20011··on Tailscale is pretty useful
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

smy20011··on Tailscale is pretty useful
Local server.

https://github.com/smy20011/MorningRadio

smy20011··on Tailscale is pretty useful
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.
smy20011··on Should managers still code?
Curious why large open source project (like linux) have no manager for all the political stuff but works well but every private company have a huge management chain for less complex stuff.
smy20011··on Grok 3: Another win for the bitter lesson
Not that simple, It could cause resource curse [1] for developers. Why optimize algorithm when you have nearly infinity resources? For deepseek, their constrains is one of the reason they achieve breakthrough. One of their contribution, fp8 training, is to find a way to train models with GPUs that limit fp32 performance due to export control.

[1]: https://www.investopedia.com/terms/r/resource-curse.asp#:~:t...

smy20011··on Grok 3: Another win for the bitter lesson
Human do write code that scalable with compute.

The performance is always raw performance * software efficiency. You can use shitty software and waste all these FLOPs.

smy20011··on Grok 3: Another win for the bitter lesson
Did they? Deepseek spent about 17 months achieving SOTA results with a significantly smaller budget. While xAI's model isn't a substantial leap beyond Deepseek R1, it utilizes 100 times more compute.

If you had $3 billion, xAI would choose to invest $2.5 billion in GPUs and $0.5 billion in talent. Deepseek, would invest $1 billion in GPUs and $2 billion in talent.

I would argue that the latter approach (Deepseek's) is more scalable. It's extremely difficult to increase compute by 100 times, but with sufficient investment in talent, achieving a 10x increase in compute is more feasible.

smy20011··on Trump's firing of the U.S. government archivist is far worse than it might seem
Looks like the beginning of the downfall of America.
smy20011··on Meta's memo to employees rolling back DEI programs
Do you have an example of such account? Most of the thing I saw is engagement bait.
smy20011··on OpenAI O3 breakthrough high score on ARC-AGI-PUB
It seems O3 following trend of Chess engine that you can cut your search depth depends on state.

It's good for games with clear signal of success (Win/Lose for Chess, tests for programming). One of the blocker for AGI is we don't have clear evaluation for most of our tasks and we cannot verify them fast enough.

smy20011··on Bluesky is ushering in a pick-your-own algorithm era of social media
Mind share the list? Asking for a friend.
smy20011··on Is This the End for X?
Then why BlueSky is #1 free apps while twitter is not?
smy20011··on Top redot developers left redot and announced a new fork of Godot
The top developer is the one who committed five PRs that changed Godot to Redot, but they had fewer than ten PRs the last time I checked.
smy20011··on Canvas is a new way to write and code with ChatGPT
A pretty good UX improvement for ChatGPT. I think they will fork VScode and make an AI editor later. Although It's confusing for me the OAI seems spend more time on end user product instead of working on AGI.
← PreviousPage 2 of 4Next →