Hacker News: theletterf

New comment by theletterf in "Don't be a meat proxy"

theletterf — Mon, 03 Aug 2026 09:30:46 +0000

There's a certain etiquette to it. When someone asks me something and I use an LLM to research the answer (notice that I said 'research', not 'produce'), I frame the findings as something that I've investigated with, say, Claude. I also take the time to edit the response and read if myself at least twice, because I don't want a stochastic machine to take over my identity.

The Seven-Action Documentation Model

theletterf — Sun, 02 Aug 2026 14:40:14 +0000

Article URL: https://passo.uno/seven-action-model/

Comments URL: https://news.ycombinator.com/item?id=49145111

Points: 1

# Comments: 0

Docs in 2026: Feed the machine, then guide the humans

theletterf — Sat, 01 Aug 2026 22:04:03 +0000

Article URL: https://passo.uno/tech-writing-role-split/

Comments URL: https://news.ycombinator.com/item?id=49138921

Points: 2

# Comments: 0

Advice for tech writers on a job hunt in the AI age

theletterf — Wed, 29 Jul 2026 16:10:34 +0000

Article URL: https://passo.uno/job-hunt-tech-writers-ai/

Comments URL: https://news.ycombinator.com/item?id=49099379

Points: 4

# Comments: 0

New comment by theletterf in "What's Under Your Feet in New York City?"

theletterf — Sun, 26 Jul 2026 19:26:11 +0000

This is fantastic, but I so hoped it would come with an infographic of NY's underworld, slice of cake style. I recall seeing one somewhere, but my attempts at finding it again all failed.

You can write docs in LLMese, but you don't have to

theletterf — Sun, 12 Jul 2026 14:47:26 +0000

Article URL: https://passo.uno/write-docs-llms-language/

Comments URL: https://news.ycombinator.com/item?id=48881610

Points: 2

# Comments: 0

Cockpit Color Guide

theletterf — Sat, 11 Jul 2026 08:13:30 +0000

Article URL: https://www.cybermodeler.com/color/cockpit.shtml

Comments URL: https://news.ycombinator.com/item?id=48869931

Points: 1

# Comments: 0

Will AI replace technical writers?

theletterf — Thu, 25 Jun 2026 09:11:40 +0000

Article URL: https://willaireplacetechnicalwriters.com/

Comments URL: https://news.ycombinator.com/item?id=48670947

Points: 3

# Comments: 1

Guadagnino's Sam Altman movie dropped by Amazon after partnership with OpenAI

theletterf — Wed, 24 Jun 2026 06:38:11 +0000

Article URL: https://www.theguardian.com/film/2026/jun/19/luca-guadagnino-sam-altman-movie-dropped-amazon-openai-artificial

Comments URL: https://news.ycombinator.com/item?id=48656024

Points: 6

# Comments: 0

Mekton (1995), mech first-person game from SGI ahead of time

theletterf — Wed, 17 Jun 2026 11:25:40 +0000

Article URL: https://www.neogaf.com/threads/mekton-1995-a-mech-first-person-game-from-sgi-ahead-of-time-from-the-remote-past.1621745/

Comments URL: https://news.ycombinator.com/item?id=48568784

Points: 2

# Comments: 0

Feed the machines, then guide the humans

theletterf — Fri, 12 Jun 2026 13:30:28 +0000

Article URL: https://passo.uno/tech-writing-role-split/

Comments URL: https://news.ycombinator.com/item?id=48503860

Points: 1

# Comments: 0

New comment by theletterf in "Fine-tuning an LLM to write docs like it's 1995"

theletterf — Fri, 05 Jun 2026 19:08:35 +0000

The Windows 3.1 theme of my blog says Hi: https://passo.uno/win31/fine-tuning-docs-llm/

New comment by theletterf in "Fine-tuning an LLM to write docs like it's 1995"

theletterf — Fri, 05 Jun 2026 16:44:47 +0000

Ha! I didn't know the origin was Shannon. It makes sense now. Big fan of my namesake Bellard. :]

New comment by theletterf in "Fine-tuning an LLM to write docs like it's 1995"

theletterf — Fri, 05 Jun 2026 12:56:29 +0000

Try Runpod or similar services: you can fine-tune stuff for the price of a latte. Stanford's NLP course recommends them: https://cs336.stanford.edu/

New comment by theletterf in "Fine-tuning an LLM to write docs like it's 1995"

theletterf — Fri, 05 Jun 2026 12:31:27 +0000

I concur. Old docs are the good stuff: https://passo.uno/why-collect-read-old-computer-manuals/

New comment by theletterf in "Fine-tuning an LLM to write docs like it's 1995"

theletterf — Fri, 05 Jun 2026 11:44:15 +0000

Interesting! I think the advantage of style fine-tuning is that you might not have to provides that much context upfront. Also, it's kind of magical to have an LLM just do something out of the box. I'll compare my local fine-tuned models against the baseline with instructions and see how they fare.

New comment by theletterf in "Fine-tuning an LLM to write docs like it's 1995"

theletterf — Fri, 05 Jun 2026 10:10:51 +0000

Had to pick a year, and most of the material hovers around the mid-90s, the golden age of MS docs. And 1995 is THE Microsoft year. :)

New comment by theletterf in "Fine-tuning an LLM to write docs like it's 1995"

theletterf — Fri, 05 Jun 2026 10:08:19 +0000

Author here. Sorry, should have made that more visible!

New comment by theletterf in "Fine-tuning an LLM to write docs like it's 1995"

theletterf — Fri, 05 Jun 2026 10:07:45 +0000

Author here. Another trick, I would argue, is consistency, hence the focus on style.

I also wrote on what I think makes docs beautiful, by the way! https://passo.uno/what-makes-docs-beautiful/

Fine-tuning an LLM to write docs like it's 1995

theletterf — Mon, 01 Jun 2026 09:48:28 +0000

Article URL: https://passo.uno/fine-tuning-docs-llm/

Comments URL: https://news.ycombinator.com/item?id=48354674

Points: 2

# Comments: 0