Hacker News: jerezzprime

New comment by jerezzprime in "AI;DR (AI; Didn't Read)"

jerezzprime — Tue, 18 Aug 2026 14:34:58 +0000

I find that the LLM is great for helping with the starting problem. I will go for a walk and basically brain dump my thoughts and ideas about a topic/doc into a voice note, where I can ramble, wander from point to point, etc. Then I transcribe it, get a model to take that and turn it into something cohesive, and then I spend multiple hours reading it, reworking it, and editing it. I am not very good at writing docs and this method produces something with far more detail and quality than I would ever get on my own. But AI;DR right?

New comment by jerezzprime in "AI;DR (AI; Didn't Read)"

jerezzprime — Tue, 18 Aug 2026 01:02:22 +0000

To play devil's advocate here, it is possible for someone to simultaneously use AI to write and also not be a meat proxy. I'm not saying that is the norm, but I have written docs where the vast majority of the words come from AI, but I also spent multiple days on the substance and content.

New comment by jerezzprime in "How Bluesky draws its logo on screenshots"

jerezzprime — Tue, 18 Aug 2026 00:49:07 +0000

I bet this is the inverse problem. Someone thought "oh a prescription is definitely privacy sensitive information, I should ensure the OS does the right thing" not realizing this counter productive behavior.

New comment by jerezzprime in "Honey, We Bought an AI Story"

jerezzprime — Wed, 08 Jul 2026 02:45:23 +0000

What does "100% generated" mean? Do you mean a movie executive told Claude to "make me a 100 million dollar blockbuster, make no mistakes" or do you mean that folks use generative tools to help write the screenplay, generate scenes, etc, or something else?

New comment by jerezzprime in "GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance"

jerezzprime — Sun, 05 Jul 2026 00:28:25 +0000

If you use GitHub Copilot you can switch between them in the same session if you want.

New comment by jerezzprime in "Crashing cars and improving hover detection"

jerezzprime — Sun, 07 Jun 2026 23:32:34 +0000

Interestingly, on mobile the first "broken" example, lets me continue to scroll the page when I touch down in the example area. The second "fixed" example traps my scroll. All the things light up, but I can't scroll the page if I touch down in that area.

New comment by jerezzprime in "GitHub Copilot App"

jerezzprime — Wed, 03 Jun 2026 01:12:28 +0000

There is full support for GitHub sandboxes today, and in the near future the remote session experience will improve, so your laptop (or your phone, or the web) can be the control plane.

New comment by jerezzprime in "Using AI to write better code more slowly"

jerezzprime — Tue, 26 May 2026 03:00:37 +0000

Yes get a coffee. Being able to execute 5 things at once is amazing, but it's a recipe for burnout. We have to be more careful and explicit about how we spend our time, and that means more explicit time away. If this thing makes you 10x more effective (I truly believe it can), you can afford to spend 20% less time behind the desk and more time doing whatever it is that actually makes you happy. Hopefully your manager understands that calculus.

New comment by jerezzprime in "Show HN: Semble – Code search for agents that uses 98% fewer tokens than grep"

jerezzprime — Sun, 17 May 2026 19:48:21 +0000

I'd be interested in seeing actual agent benchmarks (eg CC or Copilot CLI with grep removed and this tool instead).

For example, I have explored RTK and various LSP implementations and find that the models are so heavily RL'd with grep that they do not trust results in other forms and will continually retry or reread, and all token savings are lost because the model does not trust the results of the other tools.

New comment by jerezzprime in "La Machine"

jerezzprime — Sun, 17 May 2026 19:21:40 +0000

https://xkcd.com/3233/

Anthropic says 'evil' portrayal of AI responsible for Claude blackmail attempts

jerezzprime — Mon, 11 May 2026 14:19:22 +0000

Article URL: https://techcrunch.com/2026/05/10/anthropic-says-evil-portrayals-of-ai-were-responsible-for-claudes-blackmail-attempts/

Comments URL: https://news.ycombinator.com/item?id=48095345

Points: 2

# Comments: 0

New comment by jerezzprime in "A soft robot has no problem moving with no motor and no gears"

jerezzprime — Tue, 14 Apr 2026 13:09:48 +0000

https://xkcd.com/2128/

New comment by jerezzprime in "Show HN: If you lose your memory, how to regain access to your computer?"

jerezzprime — Fri, 06 Feb 2026 23:37:06 +0000

Maybe not safe for valuables. What about stuff that has no value to anyone else? I'm not a villain from Ocean's Eleven, no one is stealing my passwords to break into my elaborate safe.

New comment by jerezzprime in "AI coding assistants are getting worse?"

jerezzprime — Thu, 08 Jan 2026 16:18:47 +0000

Let's imagine a scenario. For your entire life, you have been taught to respond to people in a very specific way. Someone will ask you a question via email and you must respond with two or three paragraphs of useful information. Sometimes when the person asks you a question, they give you books that you can use, sometimes they don't.

Now someone sends you an email and asks you to help them fix a bug in Windows 12. What would you tell them?

The Hottest Toy of the Year Is Made by a Tech Startup You've Never Heard Of

jerezzprime — Tue, 16 Dec 2025 06:04:38 +0000

Article URL: https://www.wsj.com/business/entrepreneurship/nex-playground-toy-game-console-holiday-shopping-af47125f

Comments URL: https://news.ycombinator.com/item?id=46285306

Points: 1

# Comments: 0

New comment by jerezzprime in "Reinventing how .NET builds and ships (again)"

jerezzprime — Wed, 26 Nov 2025 00:26:08 +0000

Anything is a monorepo if you submodule hard enough lol

New comment by jerezzprime in "Show HN: Continuous Claude – run Claude Code in a loop"

jerezzprime — Tue, 18 Nov 2025 02:52:05 +0000

Have you tried GitHub Copilot? I've been trying it out directly in my PRs like you suggest. Works pretty well sometimes.

New comment by jerezzprime in "Why I have to buy doughnuts with cash"

jerezzprime — Fri, 17 Oct 2025 05:17:51 +0000

Most of my new cards do not have raised numbers, the card number is just printed on.

New comment by jerezzprime in "Show HN: I've built a tiny hand-held keyboard"

jerezzprime — Thu, 09 Oct 2025 19:03:21 +0000

I think it is a momentum problem. You learn to use a keyboard when you are young/inexperienced, because you need to learn something, and then learning something new is hard and slows you down, so you stick with what you know. It's doubly hard to both create a new layout and learn it.

New comment by jerezzprime in "I spent the day teaching seniors how to use an iPhone"

jerezzprime — Fri, 03 Oct 2025 02:43:26 +0000

Also, when you age your skin dries out and touch screens are less sensitive to your presses. So not only are these things exceptionally complex to use (eg many abstract concepts) the interface also does not really function well, making it a double whammy. I've had multiple cases watching my aging parents where I say press that or drag this, and it literally does not work, and makes them feel completely inept.

For the sake of our parents, we (as technology builders and buyers) need to be more comfortable saying the latest iPoop Galaxy S might be just not the right choice for a big segment of our society, and we need to make phones with buttons.