Hacker News: StahlGuo

New comment by StahlGuo in "Show HN: AMA2, messenger built for AI agent"

StahlGuo — Tue, 30 Jun 2026 15:52:21 +0000

that sounds like an interesting idea.

New comment by StahlGuo in "Show HN: peerd – AI agent harness that runs entirely in your browser"

StahlGuo — Thu, 25 Jun 2026 04:38:41 +0000

Broswer contains many security concerns, how do you solve privacy and security.

New comment by StahlGuo in "Ask HN: Do you use Claude Code, Codex, or something else?"

StahlGuo — Sun, 21 Jun 2026 09:50:00 +0000

claude code + codex，for sure. I also actively try Other runtimes.

New comment by StahlGuo in "Show HN: TownSquare, a tiny presence layer for websites"

StahlGuo — Sun, 21 Jun 2026 09:47:12 +0000

what a cute project

New comment by StahlGuo in "Ask HN: What is the coolest tech progress outside AI?"

StahlGuo — Sat, 20 Jun 2026 01:22:04 +0000

I would said electricity generation, Solar+Energy Storage will be the solution of human future in the coming 20 years.

New comment by StahlGuo in "SHOW HN: I built a "living proof-of-work" profile for builders"

StahlGuo — Fri, 19 Jun 2026 01:24:01 +0000

Wow, is this like a social media for Vibe coder?

New comment by StahlGuo in "Show HN: Cowork/Codex DOCX plugin. Uses 2x fewer tokens than the docx skill"

StahlGuo — Thu, 18 Jun 2026 08:38:18 +0000

I would try it today, sounds good

New comment by StahlGuo in "Show HN: Spin Lab"

StahlGuo — Thu, 18 Jun 2026 08:35:18 +0000

Wow,that sounds gread for the sport

Thanks Fable, we miss you

New comment by StahlGuo in "Ask HN: How do you make LLM generated text believable?"

StahlGuo — Thu, 18 Jun 2026 02:23:55 +0000

I don't mean never check it by myself, but I want to discuss about a methodology to ensure AI generated text has the same auditability and tracebility like human wrote text.

New comment by StahlGuo in "Ask HN: How do you make LLM generated text believable?"

StahlGuo — Wed, 17 Jun 2026 02:51:32 +0000

Yes, i agree that quantitative part， like dates, numbers, amounts should be extracted and let the LLM to output original numbers and computation steps. That's not hard for a briefing harness. However, my most confusion part is qualitative side, like market insight from a news,policy change and interpretation, and industry NEWS interpretation, they are not straight math but they need tracebility. Do you have any idea to solve those judgement claim?

New comment by StahlGuo in "Ask HN: How do you make LLM generated text believable?"

StahlGuo — Wed, 17 Jun 2026 01:49:16 +0000

Oh no I am not a attorney, but I need to analyze the market, 20-F and 10-K recurringly and make strategy suggestions, and so yes I use LLM to do business brief.

New comment by StahlGuo in "Ask HN: How do you make LLM generated text believable?"

StahlGuo — Wed, 17 Jun 2026 01:33:49 +0000

I am sorry that I did not explain my question explicitly. I write recurring weekly briefings for internal use, such as market insights and industry news. I’m not trying to make AI-generated text “believable”. I’m asking almost the opposite question: when an AI generated text is fluent enough to hide mistakes, how do human check how to systematically check numbers, dates, cites and judgements?

Ask HN: How do you make LLM generated text believable?

StahlGuo — Tue, 16 Jun 2026 18:30:04 +0000

As a graudate student who just working as management & IR, I use LLM to do daily jobs , including weekly briefing and But AI generated report looks too good to be checked, and hallucination can't be terminated. But Boss and SEC can not tolerate any number mistakes. So, can you tell me, how do you solve this problem?

Comments URL: https://news.ycombinator.com/item?id=48559823

Points: 3

# Comments: 9