Hacker News: Culonavirus

New comment by Culonavirus in "If Claude Fable stops helping you, you'll never know"

Culonavirus — Wed, 10 Jun 2026 14:41:57 +0000

Careful, someone may drop another whine article about HN being anti-ai (meanwhile nothing can be further from the truth, HN is one of the most, if not THE most, pro-AI news agg sites out there)

New comment by Culonavirus in "LLMs are eroding my software engineering career and I don't know what to do"

Culonavirus — Mon, 08 Jun 2026 16:51:06 +0000

Not sure about Docker (lol) but stakeholders are definitely more open to "building your own" now. It used to be that to be agile as a business you would seek out already built software and rent it, as it typically was cheaper than building and maintaining your own (I say typically due to stuff like vendor lock-in and such). But these days, and especially in 2026 with the widespread use of agents and harnesses, that formula has started to change. Even though the SOTA models are really good now, it's the harness and the "fluff" around the model that makes it a game changer. The developer is no longer the one writing or even gluing the code together, the harness does that. Pair that with context preserving mechanisms and tools that emerged (automatic context compaction, AGENTS, TOOLS, MCP...) and you can get to a state where you start a new thread in Codex and it knows your systems, your dbs, can smartly explore code it doesn't know and db data patterns etc., it can explain stuff to a new developer (and be correct most of the time and have time to spend on the developer)... all of which SIGNIFICANTLY reduces the risk you take on yourself as a company when you "build your own". What's $10k/year to any half-working semi-profitable company? Nothing. But in 2026, you can build and maintain A TON of software for that, much more than your "average IT needs" company may ever use.

I'm sure the very large (and very small) businesses will keep their absolute need for (or the lack of) inhouse developers, but everything in between will probably get compressed to one or two inhouse architects in direct contact with the stakeholders and the rest will be contractors working with Codex-like automation.

New comment by Culonavirus in "Changing how we develop Ladybird"

Culonavirus — Fri, 05 Jun 2026 14:59:51 +0000

> the maintainers are equally capable of prompting Claude Code themselves

I'm 100% on the side of maintainers here, but this is BS. If you could "just prompt Claude yourself" the AI productivity boosts would be in hundreds if not thousands of percent, which is demonstrably and self-evidently not the case (at least as of June 2026).

New comment by Culonavirus in "I was recently diagnosed with anti-NMDA receptor encephalitis"

Culonavirus — Thu, 04 Jun 2026 13:34:49 +0000

> Their is something

New comment by Culonavirus in "SQLite is all you need for durable workflows"

Culonavirus — Sat, 30 May 2026 21:15:55 +0000

Yeah these are deeply unserious people.

New comment by Culonavirus in "Starship's Twelfth Flight Test"

Culonavirus — Wed, 20 May 2026 23:25:02 +0000

Booster dry mass savings of around one ton per engine iirc.

New comment by Culonavirus in "Gemini 3.5 Flash"

Culonavirus — Wed, 20 May 2026 00:59:16 +0000

Doesn't need to be the Chinese. It can be anyone without stratospheric Nvidia margins. The Gold Rush phase of AI economy (aka "the bubble") is beginning to slow down and the Optimization phase is just beginning to ramp up (we see this with massive bumps to token cost and token burn rate of pretty much all frontier models, plus the general pivot away from your typical individual chat end-users to businesses and employees of said businesses) and there will come a time when "nvidia has the best software stack" will not mean much for the big players. Organically, I think it already kinda does, it's just masked with the inertia of massive circular deals and Nvidia selling its services to itself (entities it backs/invests in).

New comment by Culonavirus in "Gemini 3.5 Flash"

Culonavirus — Wed, 20 May 2026 00:47:43 +0000

This is not meant as an insult, but have you actually LLM/vibe coded anything that used a fast(-ish) moving library or framework? Try asking your favorite LLM with say Jan 2025 knowledge cutoff (or pretraining data cutoff, whatever you want to call it) to work on something using a framework that had a big rewrite later that year (which would make it one year old now, which is like ages in the LLM coding era)... It's a nightmare full of wrestling with the LLM when you try to tell it the version of the framework and that it changed a lot from the previous version and yadda yadda long story short down the thread when context runs out and/or is compressed it begins to forget detailed instructions and just falls back to pulling out old patterns it "remembers" from pretraining. And so you need to constantly remind it what you work with and "oh hey this doesnt work because we're working with react router v7 in framework mode, remember? not react router v6". Or try to use the latest non-lts/breaking version of a library, at first it looks it up online, but again as you get deeper into the weeds and little details, the struggle begins.

So, as far as I'm concerned, training cutoff is still a big deal.

New comment by Culonavirus in "Gemini 3.5 Flash"

Culonavirus — Wed, 20 May 2026 00:22:51 +0000

Well clearly it's not working lmao

New comment by Culonavirus in "I don't think AI will make your processes go faster"

Culonavirus — Mon, 18 May 2026 04:12:19 +0000

Lol if you know you know (I'm becoming paranoid... I think... help)

New comment by Culonavirus in "A recent experience with ChatGPT 5.5 Pro"

Culonavirus — Sun, 10 May 2026 09:54:54 +0000

hooo nooo

New comment by Culonavirus in "DNSSEC disruption affecting .de domains – Resolved"

Culonavirus — Wed, 06 May 2026 00:09:29 +0000

Ok children, sit down and listen, uncle Culonavirus will tell you a story:

"It all began with the decommissioning of the last nuclear power plant, ..."

New comment by Culonavirus in "DeepClaude – Claude Code agent loop with DeepSeek V4 Pro, 17x cheaper"

Culonavirus — Mon, 04 May 2026 05:06:44 +0000

We're not yet at a point of saturation when all the frontier models would be of somewhat comparable "intelligence" and we could decide which to use based on other factors (speed, effective context window etc.), so I honestly don't see why would you (as a company or an employee) not use the best available model with the highest (or at least second highest) thinking effort. The fees are not exactly cheap, but not that expensive either.

New comment by Culonavirus in "OpenAI’s o1 correctly diagnosed 67% of ER patients vs. 50-55% by triage doctors"

Culonavirus — Mon, 04 May 2026 04:46:47 +0000

Yeah... No. I can't possibly disagree with this view more.

I don't need to "talk to a human", I need a problem with my meatbag resolved.

> humans need other humans and human problems can't be solved with technology

WTF are you talking about? Is this bait? You can't possibly mean this. Yes humans are social creatures, but what does that have to do with medicine? Are you talking about a priest, a witch doctor, a therapist? Because if you're not, that sentence is utter BS.

New comment by Culonavirus in "A Gopher Meets a Crab"

Culonavirus — Sat, 02 May 2026 15:41:48 +0000

It's one of the best use cases for LLMs IMO. Programmers being empowered to do stuff they wouldn't dare before and/or do what they know, but faster. Having a person who never wrote much code (if any) before is a recipe for disaster because LLMs, even latest models with CC/Codex make mistakes and often code where a happy path (kinda) works, but edge cases don't . You have to check and iterate and specify. But also, programmers (seniors at the very least) have an intuition about how the system should work and they know algorithmization in general. They know how to do a thing in pseudocode on paper. In the end, you become kind of an architect of the system. LLMs give you the ability to choose the right tool for the job even if you have suboptimal or even very little experience with the given tool. There are footguns of course and I wouldn't work on say a system handling client money (banks...) this way, but most uses can take it.

As far as being taught a new language and its ecosystem through an LLM, is SO much faster than reading a book + documentation, it's like asuperpower.

New comment by Culonavirus in "Who owns the code Claude Code wrote?"

Culonavirus — Wed, 29 Apr 2026 04:30:47 +0000

> Software written by AIs are also not expressions of human creativity

I mean I'm not the biggest fan of AI on the planet by any means (which I think my post history would prove, lol), but isn't prompt design and steering the AI "human creativity"? In one of my AI-assisted projects I spent like a week in unending threads of posts trying to make the AI do stuff the way I wanted, testing the output, finding a bazillion of bugs and "basic bitch" solutions, asking for more robust this and edge case that. It felt like I wrote a novel. How is that not creativity (Crayon-eater or Picasso, creativity is creativity)?

New comment by Culonavirus in "GitHub Copilot is moving to usage-based billing"

Culonavirus — Mon, 27 Apr 2026 23:07:10 +0000

Yes there's no Opus at all on Pro. GPT 5.5 is also missing. Then again what would you expect, the economic reality is beginning to hit. Also I can't be too mad when the "base" models (GPT 5.4...) are still available and decent.

When I see how fast Codex max thinking GPT 5.5 eats our enterprise seat credits almost anything else seems cheap (until we switch our live systems from 5.4 api to 5.5 api I guess)... good thing I'm not the one paying for those credits and tokens (which is probably how most of the money is going to be made on AI going forward, borderline free chatbots for normies are done)

New comment by Culonavirus in "OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API"

Culonavirus — Sat, 25 Apr 2026 00:16:03 +0000

I hope it doesn't work and they don't post about it.

New comment by Culonavirus in "GPT-5.5"

Culonavirus — Fri, 24 Apr 2026 00:08:55 +0000

It's less than 67, duh.

New comment by Culonavirus in "SpaceX says it has agreement to acquire Cursor for $60B"

Culonavirus — Wed, 22 Apr 2026 05:24:17 +0000

> lawyers

Best I can do is pretend to be a lawyer and forward all of ur stuff to ChatGPT Free. U down?