Hacker News: bcrosby95

New comment by bcrosby95 in "JetBrains reports revenue growth, net financial loss for 2025"

bcrosby95 — Tue, 06 Oct 2026 15:46:50 +0000

The problem with hand review I always had was trying to teach the other person. You don't want to present them with an avalanche of problems. So you pick the most important 5. Over time this iterates and you build someone good at what they do.

The good part of LLMs is you don't have to worry about overloading them: you can just outline every problem with the code they produce.

The bad part of LLMs is they don't really "get better" at this stuff. I'm not training a human, and there's a limited amount LLMs can learn. So the training phase never really ends - it's Eternal September.

There's also the problem of this ultimately being my code. It isn't Claude's - Claude isn't a person.

I still read the code. I use LLMs to review it. But I also review it myself. Ultimately its faster than before, and probably better quality (because I can just give all the problems to the LLM), but slower than people doing zero review.

New comment by bcrosby95 in "JetBrains reported a net financial loss first time in its tracked history"

bcrosby95 — Tue, 06 Oct 2026 15:22:45 +0000

I mostly use it to review and tweak the changes LLMs make. However it feels like a pretty weak use case for the price involved.

New comment by bcrosby95 in "Germany’s RobCo hits $1B valuation"

bcrosby95 — Mon, 05 Oct 2026 16:01:51 +0000

How do you define good/bad? People mostly seem to talk about wait time for socialized health care, but where we live in US there's plenty of specialists that you gotta book months ahead of time. When my mom needed a pacemaker it was a 4 month process. My wife's OBGYN is booked a year out - god help you if you miss an appointment. Anyone working in pediatrics look like zombies.

Urgent care clinics have been big in our region. The primary system is obviously overloaded, and 2 of these have popped up in the last 3 years. It's more expensive per visit than our primary physician, but cheaper than an ER visit, which could easily take half a day anyways.

New comment by bcrosby95 in "Ask HN: What are you reading?"

bcrosby95 — Tue, 29 Sep 2026 22:20:22 +0000

City of Stairs

New comment by bcrosby95 in "The problem is not AI code, but not knowing about system architecture or intent"

bcrosby95 — Mon, 28 Sep 2026 18:12:42 +0000

This ties into my experience: greenfield projects turn bad way faster than legacy ones, because AI has no established patterns to key off and it does increasingly dumb shit.

New comment by bcrosby95 in "Coding is not solved"

bcrosby95 — Mon, 28 Sep 2026 15:53:21 +0000

This is why it's good to not keep your prototype a pile of shit as it grows to 5k, 10k, 50k, 100k lines of code.

New comment by bcrosby95 in "ASML says it sold 'absolutely nothing' in Europe in 2026"

bcrosby95 — Sun, 27 Sep 2026 15:07:42 +0000

The US has papered their problems over largely because of its wildly successful service companies. Who knows what that looks like with the increasing utility of LLMs though.

New comment by bcrosby95 in "ASML says it sold 'absolutely nothing' in Europe in 2026"

bcrosby95 — Sun, 27 Sep 2026 14:47:26 +0000

ASML is selling $300 million dollar machines that are fairly small for it's price point. Regulation is going to have very little impact on producing something like that vs mass produced widgets, cars, or chips.

New comment by bcrosby95 in "Opus 5.5 is good at explainer videos"

bcrosby95 — Fri, 25 Sep 2026 12:36:31 +0000

People used to say someday you can sit around all day and create things. Now they say you can go into the trades and build someone's house or something.

New comment by bcrosby95 in "AI coding has made CI a bottleneck, so we reworked ours to keep up"

bcrosby95 — Tue, 22 Sep 2026 15:31:00 +0000

Will do. I took your advice and asked Claude what it thought and it said you're exhausting.

New comment by bcrosby95 in "I Don't Like LLMs"

bcrosby95 — Thu, 17 Sep 2026 15:16:31 +0000

Pointing to luck renders all advice meaningless.

New comment by bcrosby95 in "How to write an effective software design document"

bcrosby95 — Mon, 14 Sep 2026 15:43:57 +0000

I think it's more important. AI gets a lot right, but sometimes it gets things wrong. The document might be the only human authored piece of text, and it will help future agents see that something is incorrect in the implementation.

New comment by bcrosby95 in "How to Write an Effective Software Design Document"

bcrosby95 — Mon, 14 Sep 2026 15:41:16 +0000

I've never been much for design docs. But I have some projects that are on again/off again and I can lose my train of thought. It seems like having one of these could help a lot with that.

New comment by bcrosby95 in "The EPA is planning to scrap public review rules for data center pollution"

bcrosby95 — Fri, 11 Sep 2026 23:40:07 +0000

> normal people feel, reasonably, that their civic responsibility is to vote in actual elections for the policy they support, not to spend their life in City Hall jawboning.

That's not how the vast majority of this works, and the average best case scenario on this you get to vote a politician out after they already fucked people over.

New comment by bcrosby95 in "HuggingFace: Security.txt"

bcrosby95 — Fri, 11 Sep 2026 16:31:33 +0000

Yeah, we need to go back to names like International Business Machines, fuck this immature "Google" or "Yahoo!" nonsense. Hell, Palantir is named after something in a book for children!

Give me something reasonable like Global Information and Retrieval Systems Inc or Worldwide Computational Services Holdings.

New comment by bcrosby95 in "Tell HN: OpenAI keeps re-enabling the 'allow training' setting"

bcrosby95 — Thu, 10 Sep 2026 15:54:05 +0000

It's pretty clear once you click on it:

> Allow your content to be used to train our models, which makes ChatGPT better for you and everyone who uses it. We take steps to protect your privacy. Learn more

New comment by bcrosby95 in "Better AI code comment detector"

bcrosby95 — Wed, 09 Sep 2026 18:34:11 +0000

Yes, my favorite codebase to work in is one full of accurate and long comments that detail that making a function call it never called would cause problems because of the details of a function that gets called 3 layers deeper.

New comment by bcrosby95 in "Anthropic researcher says more than 10% chance AI "could kill all humans""

bcrosby95 — Wed, 09 Sep 2026 15:58:12 +0000

Meatspace is hard though. But if LLMs solve the virtual part, maybe we can iterate quickly on robots.

Also, if you think it's annoying when Claude goes down while coding, just wait until a robot is in the middle of fixing a leak it just caused.

New comment by bcrosby95 in "Anthropic researcher says more than 10% chance AI "could kill all humans""

bcrosby95 — Wed, 09 Sep 2026 15:31:48 +0000

Why would they do that? It wouldn't accomplish anything useful.

New comment by bcrosby95 in "I resigned from Anthropic today"

bcrosby95 — Wed, 09 Sep 2026 06:29:14 +0000

The first thing LLMs seem likely to automate is automation itself. I'm curious what the past few hundreds of years of industrialization would have looked like if the first thing they automated was building, designing, and running the factories themselves.