Hacker News Reader

Hacker News

Comment by chambertime | Hacker News Reader

Parent Full thread

chambertime

Thanks for that insight on how the Chinese labs are perceived amongst hardware engineers.

I know pie charts are decisive. I thought they were visually helpful in this instance.

View on HN

> thought they were visually helpful in this instance

If you're the author, can you comment on whether you used AI to write this? (Specifically, the text.)

Where it might be suffering is in its presentation of a list of facts unorganised around any thesis. It took me until your China Question section to see the meat of your piece.

If I had to suggest some edits, they would be making everything above that section more concise (by reducing the number of charts and/or moving them to footnotes) and adding a summarising subtitle.

There are also jargon jumps, e.g. from TFAB to TCB. (I initially assumed the FAA was a TCB, the latter being a generic international term.) This compounds the lack of conciseness presented by the accredition-body breakdown and TCBs vc. test-only labs sections. If those sections were moved after your thesis section, you could dive into whether China's labs differ from the U.S. labs in those respects.

The content of the site is, as stated in my first comment and in the article itself, a nice looking wrapper on top of in essence, an llm Wiki that I put together with the help of Claude on the hardware certification universe. While I was building this data set out, I uncovered that the FCC had this vote today, so I thought it would be a good thing to share since it's timely and because I had just collected all of the relevant information tolp someone figure out how this impacts their hardware certification process (I use voice transcription to write this comment)

I very much appreciate your feedback. As I look at the article now. I totally see what you're saying. I should have let off what was going on with the vote today since that's what I referenced in the title of the post on here.

the headline hints that there's some sort of non-obvious factor that's going to be revealled. I scrolled past countless redundant and information-sparse graph-like figures and never found it; moved on.

If you've only got a paragraph worth of information to share, say it and let us get on with our lives.

Well I couldn't find any other thorough dataset on this topic, so in that sense this is non-obvious since it took weeks to assemble the information. And it was fun doing it using the LLM Wiki technique.

> it was fun doing it using the LLM Wiki technique

What is that?

https://gist.github.com/karpathy/442a6bf555914893e9891c11519...

Could you share the tools you used to do this? I'd love to organise my esoteric research side quests like this.

Git + claude code in yolo mode. In the first prompt, I passed it Kaparthy's gist, and had it put together a high level plan of all of the sections that needed to be written to complete a vision I provided. Essentially put together a complete wiki on everything for getting global hardware certification.

I then had it loop once an hour. It would pick the next wiki to write, research it, gather raw sources, and then synthesize the wiki for me and push. I could nudge it in between hours if I wanted.

Do you add this as a skill or permanent prompt, making it always maintain wikis in the background? Or do you direct it to make these only when you're in the project?

There's skills if you want. I didn't want to do that since I don't feel like I need the smarts to work on the LLM wiki in every coding session. I like to keep my context clean and scoped to what I'm working on.

I am running this in a long running session that spawns a subagent once an hour. So the context of the main session doesn't get out of control.

The general idea is to have the LLM maintain longer-term context/background by storing it in a format/structure that's akin to a standard Wiki. The result is (hopefully) a series of human-readable and editable documents that's developed and maintained by the agent.

There's great coverage of it at https://gist.github.com/karpathy/442a6bf555914893e9891c11519...

It's actually also now a base capability in the Hermes agent and has been really helpful for me, at least.

Reply on news.ycombinator.com