Hacker News: prymitive

New comment by prymitive in "Over 170k Nonprofits Lost All Their Data. Is Microsoft to Blame?"

prymitive — Mon, 24 Aug 2026 09:27:25 +0000

Saying sorry means admitting guilt. If there’s guilt there some level of harm. If there’s harm you can be sued. Avoiding being sued due to causing harm usually means increased costs, because you now need to take care you didn’t take before. Higher cost means you’re less competitive. Being less competitive makes you less attractive investment target. So as always it’s all about money. Saying sorry == lower share price.

New comment by prymitive in "Opus 5.0 drives incoherence into the stratosphere"

prymitive — Wed, 19 Aug 2026 18:23:40 +0000

I find it particularly bad at writing test comments, I usually start fixing bugs by adding regression tests and Opus tend to put story into comments for these, including “but it fails because…” followed by bug description including line numbers and call chains. It just lives to narrate everything

New comment by prymitive in "Opus 5.0 drives incoherence into the stratosphere"

prymitive — Wed, 19 Aug 2026 18:15:33 +0000

Sounds like engagement KPIs are through the roof since 4.8

New comment by prymitive in "We eliminated 1,400 CVEs in NanoClaw's container images"

prymitive — Thu, 13 Aug 2026 16:59:51 +0000

For those unfamiliar, “CVE” stands for “CV Enrichment”, common slang in Posture Engineering

New comment by prymitive in "Humanising LLM Outputs Is Dumb"

prymitive — Mon, 10 Aug 2026 18:21:02 +0000

+1 it’s a tool

It’s not perfect, it has shortcomings, it sometimes produces bogus outputs. All of that is fine for a tool, it’s not fine when it pretends it’s a conscious being, because errors start to feel like lies and it becomes a bit too personal.

Windows 11's Weather app uses ~1GB RAM

prymitive — Sun, 09 Aug 2026 18:33:25 +0000

Article URL: https://www.omgubuntu.co.uk/2026/08/linux-vs-windows-weather-app-ram

Comments URL: https://news.ycombinator.com/item?id=49234179

Points: 5

# Comments: 1

New comment by prymitive in "Don't be a meat proxy"

prymitive — Mon, 03 Aug 2026 07:25:46 +0000

I think a lot of that is people who were always very insecure because they’re mediocre engineers. Previously asking questions or not understanding something was a bit painful but now you can hear “you’re absolutely right!” and make progress all day every day. Until you need to interact with actual humans and that’s why you try to minimise it, hiding behind ai generated content.

New comment by prymitive in "Google fixed more Chrome bugs in June than over the past two years, thanks to AI"

prymitive — Sat, 01 Aug 2026 11:42:33 +0000

To be fair it’s also worth noting that it’s much easier to find a buggy edge case with existing code than it is to write bug free code that doesn’t have any edge cases at all. It’s so much easier to read some concrete logic and find holes in it, than it is to start from nothing and end up with perfection. It’s true both for humans and agents, but agents are better are validating correctness.

New comment by prymitive in "AI doesn't generate working products, that's still your job"

prymitive — Sat, 01 Aug 2026 10:53:00 +0000

There’s been infinitely times where I was stuck at some problem and every single solution was complex, messy, over-engineered and somehow wrong, until I went on a walk or moved to a different issue and suddenly it would hit me that I was looking at it all wrong, and there’s a simple solution there but my tunnel vision didn’t let me see it. LLM rob you of that, everything is instant, there’s no time to reflect, there’s no time to realise it’s a dead end, or that it won’t work with the next problem on your todo list.

New comment by prymitive in "Anthropic finds three hacking incidents similar to the HuggingFace attack"

prymitive — Fri, 31 Jul 2026 07:44:07 +0000

Anthropic Needs to have the most intelligent and scary agents, so if OpenAI does something bad they need to prove their models can do even worse. Without that the whole valuation collapses. There’ll be more “our model outhacks others” for the next hype cycle.

New comment by prymitive in "GCC steering committee announces AI policy"

prymitive — Thu, 30 Jul 2026 12:38:05 +0000

Is it "anti-LLM" or is it anti "here's some code I don't understand that a machine generated for me kthxbye"? Code is not just code, it's also liability and trust.

New comment by prymitive in "Sam Altman says people don't want an AI to act as CEO"

prymitive — Wed, 29 Jul 2026 06:51:44 +0000

The invention of modern day CEO will always be celebrated throughout history, such a gift to the world.

New comment by prymitive in "Our position on open-weights models"

prymitive — Tue, 28 Jul 2026 08:30:49 +0000

A bit of good old “it’s really good idea, I love it, great effort … BUT”

Mixed with “if kids can’t get semi dangerous drugs from the back of my van then they will be forced to buy from even shadier, more dangerous dark web van”

New comment by prymitive in "What is happening to jobs? Separating AI hype from reality"

prymitive — Sun, 26 Jul 2026 12:24:32 +0000

I'm sure Anthropic would love for everyone to believe that soon they will be the sole provider of "skills" for the entire planet and every single business transaction is done as a part of the subscription they offer - people sell AI generated content and other people's agents buy that - they're the entire world economy. I'm sure such narrative would help them reach infinity market valuation for the upcoming IPO.

New comment by prymitive in "Engineering management after the cost of code collapsed"

prymitive — Sat, 25 Jul 2026 20:57:41 +0000

I have never seen a plan written by LLM that wasn’t vague and light on details, every time I need to ask for more details and every time I ask to implement it trips over some dead end in the plan, discards the plan and continues as if there was no plan to begin with. Planning feels often just narrating the request and a wish list then what a human would do - methodically build enough understanding so that you’re confident of the direction you choose. LLM plans are overhyped and overrated.

New comment by prymitive in "What if we made advertising illegal?"

prymitive — Fri, 24 Jul 2026 22:21:38 +0000

Every idea taken to extreme becomes unbearable. I ask friends for recommendations on what to read or watch, and I enjoy doing that. But if they would follow me around everywhere and keep suggesting things non stop purely because they make money out of it then they would stop being my friends very quickly.

New comment by prymitive in "Starlink unlimited aviation plan to rise from $10k/month to $20k"

prymitive — Wed, 15 Jul 2026 17:16:33 +0000

Here’s an idea: Musk launches a ton of orbital gpus but in reality it’s just an empty shell and real gpus sit in unused grok data centres. How would we even know?

New comment by prymitive in "The Tower Keeps Rising"

prymitive — Tue, 14 Jul 2026 17:26:18 +0000

It used to be that you need a good reason to make huge refactorings, because it’s often so much work. Now agent can rewrite half of your code if your prompt is vague enough and you don’t actual try to review it all. And so the “soul” of a program can change dramatically every single day. It’s both great and very much not so.

New comment by prymitive in "How to stop Claude from saying load-bearing"

prymitive — Tue, 14 Jul 2026 16:44:43 +0000

How do you manage to make Opus follow any rules? Maybe it’s a windsurf thing but I have a ton of custom rules and Opus just ignores most of them. GPT on the other hand follows them like it’s a cult - if I have a rule I can’t ever force it to ignore it. Opus just doesn’t care. If I ask why it’s not following rules it will apologise and suggest creating a rule for it …

New comment by prymitive in "Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k"

prymitive — Sun, 12 Jul 2026 19:03:59 +0000

I often find myself annoyed when Opus fixes a typo in a comment and decides to run tests, lints and whenever else it can find to run. Often it will start by stashing current changes just to preemptively check if all tests were passing before. And I can blame myself a bit because my rules do say: verify all changes with tests. But as there is that I in AI that is hyped which you’d think means it knows not to put tomatoes into fruit salad …