Hacker News: planb

New comment by planb in "AI subscriptions are a ticking time bomb for enterprise"

planb — Sun, 17 May 2026 16:05:22 +0000

If that’s true, then it will be even cheaper to provide them as a subscription. Following your logic, every company would be running their own data centers instead of using cloud providers.

Nginx Rift Heap-based Buffer Overflow

planb — Thu, 14 May 2026 16:51:05 +0000

Article URL: https://depthfirst.com/nginx-rift

Comments URL: https://news.ycombinator.com/item?id=48137939

Points: 1

# Comments: 0

New comment by planb in "Computer Use is 45x more expensive than structured APIs"

planb — Tue, 05 May 2026 17:31:06 +0000

This will not happen. None of the existing apps people use daily on their phones have any incentive to support this. Social media wants the people to doomscroll, shopping apps and booking sites want to use their own dark patterns to make people believe they get a special discount if they buy _now_ and everything else just wants users to see the ads. Why on earth would they offer convenient hooks for AI chatbots?

New comment by planb in "ASML's Best Selling Product Isn't What You Think It Is"

planb — Mon, 04 May 2026 13:08:44 +0000

You're absolutely right! "Why Does This Matter?" was a dead giveaway that this article was not written by a human — it was written by a large language model.

But really: "Why does this matter?" When looking at an article like this, I rarely read the text. This is just fluff no matter if AI-generated or hand written. The info is "there's a LEGO set of that ASML machine" and the picture of that set. That's all I want to know before clicking the back button.

New comment by planb in "John Ternus to become Apple CEO"

planb — Tue, 21 Apr 2026 08:56:25 +0000

But there is interesting information in lots of the comments. Like the quote from Ternus about Apple Maps in one of the comments. This gives relevant insight of how he thinks and how he might handle problems when he takes over.

New comment by planb in "Codex for almost everything"

planb — Mon, 20 Apr 2026 18:41:27 +0000

I’m not doing that. That would be like giving my child shell access to my system.

New comment by planb in "Codex for almost everything"

planb — Fri, 17 Apr 2026 14:45:42 +0000

Yes, but none of this applies to the local codex agent that runs when I tell it to and has access to my computer. Like: „scan this folder of PDFs and create an excel file with all expenses. Then enter them into my tax software.“ This needs access to very sensitive data and involves a quite complex handling of data. But the only attack vector I see is someone injecting prompts into my invoice files.

New comment by planb in "Codex for almost everything"

planb — Thu, 16 Apr 2026 19:33:12 +0000

Why would my agent retrieve that lunch menu?

New comment by planb in "Codex for almost everything"

planb — Thu, 16 Apr 2026 18:07:47 +0000

How many of these threat vectors are just theoretical? Don’t use skills from random sources (just like don’t execute files from unknown sources). Don’t paste from untrusted sites (don’t click links on untrusted sites). Maybe there are fake documentation sites that the agent will search and have a prompt injected - but I haven’t heard of a single case where that happened. For now, the benefits outweigh the risk so much that I am willing to take it - and I think I have an almost complete knowledge of all the attack vectors.

New comment by planb in "Apple's accidental moat: How the "AI Loser" may end up winning"

planb — Mon, 13 Apr 2026 18:29:46 +0000

Source? But it‘s true that I forgot about the Google Search deal.

New comment by planb in "Apple's accidental moat: How the "AI Loser" may end up winning"

planb — Mon, 13 Apr 2026 10:17:07 +0000

Services revenue is mostly just 30% from App Store Sales. This means every time a user clicks a pro account for ChatGPT or Claude on their phone, Apple makes more money than they could make with a self deployed model.

New comment by planb in "So where are all the AI apps?"

planb — Tue, 24 Mar 2026 18:33:30 +0000

Can you give me any new (i.e. released in 2026) app that does something useful? There's just not many good app ideas left after all..

New comment by planb in "Don't post generated/AI-edited comments. HN is for conversation between humans"

planb — Fri, 13 Mar 2026 09:26:55 +0000

Absolutely. That was exactly how I meant it! Indeed that meaning was a bit lost in the LLM version.

New comment by planb in "Shall I implement it? No"

planb — Fri, 13 Mar 2026 09:21:33 +0000

Nobody said that. But as you say, it's just a tool. Tools need to be used correctly. If tools are unintuitive, maybe that's due to the nature of the tool or due to a flaw in it's design. But either way, you as the user need to work around that if you want to get the maximum use out of the tool.

New comment by planb in "Shall I implement it? No"

planb — Fri, 13 Mar 2026 09:10:56 +0000

You're absolutely right! No, really: I've never had this problem of unprompted changes when I'm just asking, but I always (I think even in real-life conversations with real people) start with feedback: "Works great. What happens if..."

I think people having different styles of prompting LLMs leads to different model preferences. It's like you can work better with some colleagues while with others it does not really "click".

New comment by planb in "Don't post generated/AI-edited comments. HN is for conversation between humans"

planb — Thu, 12 Mar 2026 05:42:54 +0000

As a non native speaker, I sometimes use LLMs to search for a way to formulate my thoughts like I intend them to be received by the reader. I'd never just copy the verbatim LLM output somewhere, it always sounds blunt and not like me, but I gladly apply grammar corrections or better phrasing.

I'd normally not do this for a text of this length, but just for fun, here's what ChatGPT suggests:

As a non-native speaker, I sometimes use LLMs to help me find wording that conveys my thoughts the way I want them to be understood by the reader. I would never copy the output verbatim, because it often sounds blunt and unlike me, but I’m happy to use grammar corrections or improved phrasing.

New comment by planb in "Show HN: Kula – Lightweight, self-contained Linux server monitoring tool"

planb — Sat, 07 Mar 2026 06:13:52 +0000

Honestly the sentence from the readme just sounds like a recommendation an LLM would make.

New comment by planb in "I built a demo of what AI chat will look like when it's “free” and ad-supported"

planb — Sun, 01 Mar 2026 19:24:41 +0000

I understand the message this tries to tell but this is not how it will look. This is how dying cash cows look. This isn’t even dangerous, it’s just ugly and wouldn’t be used by many people.

The real thing will look like ChatGPT. It will even answer WAY faster, because every microsecond means real money. The answers will sound real. They will even be useful. But maximally engaging. Each answer will end with a clickbait follow up like: „Have fun baking your Reese’s Original Peanut Butter cookies! Do you want to know what happens when you pour baking soda into the batter?“

I really hoped for that experience when clicking the headline.

New comment by planb in "EDuke32 – Duke Nukem 3D (Open-Source)"

planb — Sat, 21 Feb 2026 21:03:06 +0000

Me too! I learnt a lot about how games „work“ by using the level editor and using more and more of the advanced features. And playing your own worlds in 1vs1 serial linked multiplayer mode was a whole new experience.

New comment by planb in "HackMyClaw"

planb — Tue, 17 Feb 2026 18:37:02 +0000

Please keep us updated on how many people tried to get the credentials and how many really succeeded. My gut feeling is that this is way harder than most people think. That’s not to say that prompt injection is a solved problem, but it’s magnitudes more complicated than publishing a skill on clawhub that explicitly tells the agent to run a crypto miner. The public reporting on openclaw seems to mix these 2 problems up quite often.