remoquete
Re:Are LLMs Random?
on Wednesday April 30, 2025 @05:39AM (#43842966)
Agreed. These tests should be performed on local models.
Re:Sycophancy in GPT-4o
on Wednesday April 30, 2025 @01:37AM (#43841601)
Using prompts know to be problematic? Some sort of... Voight-Kampff test for LLMs?
Re:Sycophancy in GPT-4o
on Wednesday April 30, 2025 @12:36AM (#43841324)
Don't they test the models before rolling out changes like this? All it takes is a team of interaction designers and writers. Google has one.
Build your own tech writing tools using LLMs
Show HN: A tool that lets tech writers test custom LLM prompts with context
https://github.com/theletterf/aikidocs/I've developed this simple tool using Copilot as a response to PocketFlow's tutorial generator, which has a hardcoded prompt with few technical writing recommendations: https://news.ycombinator.com/item?id=43739456I think tech writers should own the prompts that generate documentation, so Aikidocs is for them to experiment using a simple, predictable...
Re:Show HN: I built an AI that turns GitHub codebases into easy tutorials
on Monday April 21, 2025 @08:29AM (#43751203)
Because you can't. See my previous comment. https://news.ycombinator.com/item?id=43748908
Re:Show HN: I built an AI that turns GitHub codebases into easy tutorials
on Monday April 21, 2025 @08:26AM (#43751174)
Indeed. Augmentation is the way forward.
Re:Show HN: I built an AI that turns GitHub codebases into easy tutorials
on Monday April 21, 2025 @02:13AM (#43748908)
This is nice and fun for getting some fast indications on an unknown codebase, but, as others said here and elsewhere, it doesn't replace human-made documentation.
Re:Claude Code Best Practices
on Saturday April 19, 2025 @10:44AM (#43736749)
What's the Gemini equivalent of Claude Code and OpenAI's Codex? I've found projects like reugn/gemini-cli, but Gemini Code Assist seems limited to VS Code?
Things I remind myself when working with others
Re:Google Is Winning on Every AI Front
on Saturday April 12, 2025 @03:39PM (#43667351)
AI-or-not silliness aside (gets boring real fast): I find Gemini to be faster (it matters), more reliable, with quality of responses being at the same level as Claude's. Better integration with Google apps and devices is a plus.
Re:Google Is Winning on Every AI Front
on Saturday April 12, 2025 @11:39AM (#43665308)
You can. Then again, I'm paying.
Re:Google Is Winning on Every AI Front
on Saturday April 12, 2025 @09:02AM (#43664012)
Could be, if an AI actually wrote it.
Re:Google Is Winning on Every AI Front
on Saturday April 12, 2025 @06:22AM (#43663102)
Ensure I only use them. It happened with search first, then mobile (Pixel), now it's LLMs.
Re:Google Is Winning on Every AI Front
on Saturday April 12, 2025 @05:22AM (#43662789)
The improvement in Gemini 2.5 is real, but I wouldn't say it's miles away from Claude 3.7. The fact that web browsing still isn't in Claude in Europe bothered me. It's many little things.
Re:Google Is Winning on Every AI Front
on Saturday April 12, 2025 @02:17AM (#43661826)
Image generation is extremely good in GPT now. Claude's edge is UX. But I doubt Google won't catch up on both fronts. It has the technology and manpower.
Re:Google Is Winning on Every AI Front
on Saturday April 12, 2025 @02:01AM (#43661748)
I was a loyal Claude user until I decided to try Gemini 2.5. "After all", I thought, "I already use a Pixel phone, so it's integrated with Android. And with Google Drive. And I can get it through my Google One subscription."
And now that I'm on it, I don't think I'm going back. Google did it again.
Re:Mass Grave of 150 Roman Soldiers Found Under Vienna Sports Field
on Monday April 07, 2025 @12:52PM (#43613456)
And CDI plans better than those in year MMXXV.
Re:US Administration announces 34% tariffs on China – 20% on EU
on Thursday April 03, 2025 @05:00AM (#43566864)
I'm wondering how this protectionist trend will impact overseas hires. Will US companies continue to hire talent remotely outside of their borders? Will they be incentivized to only hire in the US?
What's wrong with AI-generated docs
Re:The average college student today
on Monday March 31, 2025 @03:32AM (#43532190)
I'm a tech optimist, but I struggle to see a fast solution to the problems described by this article that doesn't involve ending apps and screens for good.
Re:How to Write Blog Posts That Developers Read · Refactoring English
on Friday March 28, 2025 @04:39PM (#43509617)
The most interesting content I found through HN had no pictures or illustrations.
Critique of Work
Re:"Normal" engineers are the key to great teams
on Friday March 14, 2025 @05:04AM (#43360777)
I'm seeing more reactions like this. I wonder if it's a consequence of reading AI generated drivel and not being able to tell content apart. Or perhaps people is asking for more action and less reaction. I don't know.
Technical writing has a depth issue
Re:Why writing small docs is a game changer
on Wednesday March 05, 2025 @02:29AM (#43263864)
I don't know. I work for a B-series startup and I'm a docs engineer.
First "Synthetic Biological Intelligence" runs on living human cells
Re:Why writing small docs is a game changer
on Tuesday March 04, 2025 @04:58AM (#43252617)
> almost nobody has (or puts in) the time to properly edit a twenty+ pages document to make it pleasant to read
That's why technical writers and editors exist.
Re:Why writing small docs is a game changer
on Tuesday March 04, 2025 @04:40AM (#43252472)
More common than you'd think...