Hacker News: inerte

New comment by inerte in "GitHub Copilot App"

inerte — Tue, 02 Jun 2026 18:50:54 +0000

I know it has the same functionality, but it also looks like the Codex app which looks like Cursor Agents! Are they sharing some VS Code primitive here?

New comment by inerte in "The Last Technical Interview"

inerte — Sat, 30 May 2026 15:06:55 +0000

Same for me. I applied for engineering manager. Was told it was going to be a code review. I found a bunch of things that it could be improved, detected a very slow part / quadratic loop, but couldn't come up with the best algo to use. It was just leetcode in disguise.

New comment by inerte in "Dynamic Workflows in Claude Code"

inerte — Fri, 29 May 2026 17:44:35 +0000

I am getting so confused when to use what... agents, sub-agents, tasks, team mates, /goal, /loop, and now workflow. Each with different degrees of effort.

Don't make me think.

All these knobs are also exposed in ChatGPT, which I am more familiar when chatting. Which one of the models? Do I go Instant, Thinking, Pro? Extended Pro? Oh no, maybe I need Deep Research.

Sometimes I think it's on purpose. I fear if I try a lowest knob, it will miss something. So turn everything up. And token usage goes up.

New comment by inerte in "Tell HN: I'm tired of AI-generated answers"

inerte — Fri, 22 May 2026 00:06:11 +0000

Dead Internet Theory and all. There is no going back. I don't think an online space can be designed to be safe from this. The AI agents can fully control our computers. All solutions that involve technology (software or hardware) are or will be flawed.

New comment by inerte in "New Nightmare Just Dropped: '3D' Animated Ads on Trucks in Traffic"

inerte — Sun, 17 May 2026 22:12:25 +0000

If you haven't seen They Live... that's next level.

Sigil Review: Semantic Diffs for Agents and Reviewers

inerte — Fri, 08 May 2026 15:06:13 +0000

Article URL: https://inerte.github.io/sigil/articles/sigil-review/

Comments URL: https://news.ycombinator.com/item?id=48064260

Points: 2

# Comments: 0

New comment by inerte in "DeepSeek V4 Pro at 75% off until 31 May"

inerte — Thu, 07 May 2026 00:57:13 +0000

I think martin_henk is fully aware of that and it's why of all the examples of how a government can use your data, he picked this one...

New comment by inerte in "Waymo Drives Off with South Bay Man's Luggage"

inerte — Sun, 03 May 2026 00:51:47 +0000

If I steal your luggage, do you expect to be paid to get it or that I return to you?

Waymo should have white-gloved this and sent Larry Page himself to deliver the luggage. This is horrible PR. Airlines will send you their luggage if misplaced. One day Waymo will drive-off with your toddler and ask you to file for adoption if you want them back.

New comment by inerte in "Meta in row after workers who saw smart glasses users having sex lose jobs"

inerte — Thu, 30 Apr 2026 15:42:39 +0000

Yes but also we don't want people live streaming murder and suicide, so there's detection and moderation in place.

New comment by inerte in "He asked AI to count carbs 27000 times. It couldn't give the same answer twice"

inerte — Wed, 29 Apr 2026 16:21:51 +0000

To be fair my expectations is that those apps have done the prompt engineering, and schema, and tools (to query nutrition database), etc... and although they're not 100% consistent, the margin of errors should be narrow to the point that barely matter, and they should do a bit better than a random ChatGPT chat session.

New comment by inerte in "Amateur armed with ChatGPT solves an Erdős problem"

inerte — Sun, 26 Apr 2026 03:00:27 +0000

I would question at $60k. At $100k is a steal.

New comment by inerte in "GPT‑5.5 Bio Bug Bounty"

inerte — Sun, 26 Apr 2026 02:00:43 +0000

Probably because the goal is to have more users, not necessarily profit per user. Netflix once had that "problem" and every lockdown increased the stock price.

New comment by inerte in "Google Flow Music"

inerte — Sat, 25 Apr 2026 00:57:02 +0000

I've tried and couldn't make it sound like Angine de Poitrine, it completely ignores the microtones. Sounds more like Polyphia. It does look like AdP is the answer to AI.... or we haven't trained the models with sufficient microtones, likely due to western music influence.

New comment by inerte in "Google Flow Music"

inerte — Sat, 25 Apr 2026 00:51:12 +0000

Because of ads and background music for YouTube.

New comment by inerte in "Habitual coffee intake shapes the microbiome, modifies physiology and cognition"

inerte — Fri, 24 Apr 2026 15:12:33 +0000

Same here, and it made me wonder, why did I go back to drinking coffee?

My best explanation is that there are effects, I just suck at self-awareness :)

New comment by inerte in "Workspace Agents in ChatGPT"

inerte — Wed, 22 Apr 2026 22:23:56 +0000

They have to be generic because it's a generic tool. If they write "this tool can arrange student field trips", people might ignore thinking it has a narrow purpose.

Yes, work is being trivialized, but the symptom here isn't caused by that.

New comment by inerte in "A Dumb Introduction to Z3 (2025)"

inerte — Sat, 18 Apr 2026 15:27:15 +0000

Like any interview, randomly. Some of them will think it's amazing, clever person, chose the best tool for the job. Other will think it's weird, person is too clever, chose the worst tool for the job.

It totally depends for WHAT you're interviewing, but unlikely the company will want Z3-backed code, so most reactions would be the later.

New comment by inerte in "Spending 3 months coding by hand"

inerte — Sat, 18 Apr 2026 01:55:35 +0000

> Can you design text data specifically to mess with LLM training?

Maybe text that costs a LOT of tokens. Very, very verbose. I think if there are rules and on the internet, LLMs can eventually figure it out, so you have to make it expensive.

Another way would be to go offline. Never write it down, only talk about it at least 50 meters away from your phone. Transmitted through memory and whisper.

I embedded Sigil's docs in its CLI so LLMs can write Sigil

inerte — Thu, 16 Apr 2026 00:45:32 +0000

Article URL: https://inerte.github.io/sigil/articles/sigil-ships-embedded-docs-for-llm-cold-starts/

Comments URL: https://news.ycombinator.com/item?id=47787324

Points: 2

# Comments: 0

New comment by inerte in "GitHub Stacked PRs"

inerte — Mon, 13 Apr 2026 21:28:35 +0000

Looks interesting, but it seems you need to know the final shape of the stack before you start creating Pull Requests. So it's useful if you create Pull Request A, then immediately start working on something that builds on top of A, create a Pull Request for that (while A is still a PR), then you can do A->B->C

Here's something that would be useful: To break down an already big PR into multiples that make up a stack. So people can create a stack and add layers, but somehow re-order them (including adding something new at the first position).