Hacker News: sleazebreeze

New comment by sleazebreeze in "Siri AI"

sleazebreeze — Tue, 09 Jun 2026 01:52:56 +0000

Too bad Google can’t compete in consumer or professional AI either

New comment by sleazebreeze in "White House's Aliens.gov Site Brags That ICE Arrested More Than 700 US Citizens"

sleazebreeze — Sat, 30 May 2026 20:48:42 +0000

They teased it as such. Reckless and stupid political stunt.

New comment by sleazebreeze in "Headway Therapy Patients Forced to Scan Their Faces to Keep Getting Care"

sleazebreeze — Fri, 29 May 2026 15:20:06 +0000

What exactly is the concern here by Headway? Are they afraid AI deep fakes will be receiving therapy?

Obviously they are doing data collection and selling training data of emotional conversations to AI labs. But what's their stated justification? I can't figure it out.

New comment by sleazebreeze in "Bun support is now limited and deprecated"

sleazebreeze — Fri, 22 May 2026 21:51:42 +0000

You aren't allowed to dismiss vibe coded software based on the slop vibes. It must be well-researched and human reviewed in order to have an opinion.

New comment by sleazebreeze in "Little magazines are back"

sleazebreeze — Sun, 03 May 2026 01:53:14 +0000

Many libraries have ebooks. I am familiar with the app Libby in parts of the US.

New comment by sleazebreeze in "Show HN: Marky – A lightweight Markdown viewer for agentic coding"

sleazebreeze — Fri, 17 Apr 2026 14:58:33 +0000

VS codes preview of markdown files scrolls very poorly on my Mac. It jumps around and scrolls slowly through certain sections.

New comment by sleazebreeze in "Claude Opus 4.7"

sleazebreeze — Thu, 16 Apr 2026 15:08:42 +0000

This made me LOL. They keep trying to fleece us by nerfing functionality and then adding it back next release. It’s an abusive relationship at this point.

New comment by sleazebreeze in "Arguing with Agents"

sleazebreeze — Thu, 16 Apr 2026 03:43:52 +0000

This was my reading too. Interesting idea, but it took 10 pages of fluff to get to it and I didn't even believe the final idea when we got there. I started off reading the first part and thought he would get to the part where he realized he was managing context wrong. Never got there, instead he thought it was about the shape of the prompt.

New comment by sleazebreeze in "Arguing with Agents"

sleazebreeze — Thu, 16 Apr 2026 03:42:02 +0000

Yes, this was super annoying to read. It was some core ideas and it was expanded into a way too long essay that boiled down to this guy doesn't know how to run agents.

New comment by sleazebreeze in "Google broke its promise to me – now ICE has my data"

sleazebreeze — Wed, 15 Apr 2026 20:22:32 +0000

Should he be harassed and deported for this?

New comment by sleazebreeze in "I built an AI receptionist for a mechanic shop"

sleazebreeze — Tue, 24 Mar 2026 23:27:07 +0000

Top of the line models still routinely get this wrong. This is just "make no mistakes" with more steps.

New comment by sleazebreeze in "Uber reported to the state that I was fired for "annoying a coworker.""

sleazebreeze — Mon, 09 Mar 2026 20:29:03 +0000

There are a lot of missing parts to the story. If we assume the author left out everything that made them look bad, and including only what makes them look good then the result is a very incomplete feeling article.

For example: they asked for guidance and then the very next thing is them being fired. How did they respond to the coworker? Something is off here - the coworker who had messaged him about non-work topics TWO days in a row - then immediately reported him for his reply. What?

New comment by sleazebreeze in "The Slow Death of the Power User"

sleazebreeze — Wed, 25 Feb 2026 20:13:43 +0000

It definitely is. I got partway through and then realized it just keeps going without a point. Classic hallmark of AI writing.

New comment by sleazebreeze in "Sizing chaos"

sleazebreeze — Thu, 19 Feb 2026 23:20:47 +0000

My apologies. I was responding to the fact that animals and humans have base instincts that steer us towards bad food choices or over-stimulations. I was considering those instincts as the incentives that can't be changed.

On a macro scale, yes I agree that we should revolt against campaigns designed to exploit our animal nature. However on a personal basis, I do believe we owe it to ourselves to take radical responsibility over our own reactions to those things.

New comment by sleazebreeze in "Sizing chaos"

sleazebreeze — Thu, 19 Feb 2026 00:30:48 +0000

You can't control the incentives, you can only control your reactions to those incentives.

New comment by sleazebreeze in "GPT‑5.3‑Codex‑Spark"

sleazebreeze — Thu, 12 Feb 2026 21:05:40 +0000

Claude code can output Excalidraw format files which can be imported directly into the webapp. You can MCP it too if you want.

New comment by sleazebreeze in "A few random notes from Claude coding quite a bit last few weeks"

sleazebreeze — Tue, 27 Jan 2026 23:40:14 +0000

People would struggle to review code in a completely unfamiliar domain or part of the stack even before LLMs.

New comment by sleazebreeze in "Why I Disappeared – My week with minimal internet in a remote island chain"

sleazebreeze — Mon, 29 Dec 2025 19:18:53 +0000

I noticed that too, I had to re-read it a few times to make sure I was understanding it properly, it seemed so out of place. Then I read the rest of the article and realized this guy has zero perspective on anything.

New comment by sleazebreeze in "You can make up HTML tags"

sleazebreeze — Mon, 29 Dec 2025 06:33:33 +0000

I see a good case for my company to use Lit for creating complex components such as highly interactive panels/widgets to be shared between React/Angular apps in our large ecosystem. However the decision was: 1. Prefer sharing plain JS/TS over framework code so try that first and 2. if the component is so complex and tricky to get right, it probably needs to be re-implemented in each framework anyways (or some sort of wrapper)

My secondary concern with Lit is the additional complexity of using shadow and light DOM together in long lived React/Angular apps. Adding a new paradigm for 75+ contributors to consider has a high bar for acceptance.

New comment by sleazebreeze in "You can make up HTML tags"

sleazebreeze — Mon, 29 Dec 2025 03:38:38 +0000

I just evaluated Lit for work and while we didn't go with it, it was very nice. I love the base custom elements API regardless of using Lit or not, turns out that's all you really need to make intricate UIs that feel seamless.