Hacker News: ketzo

New comment by ketzo in "Anthropic expands partnership with Google and Broadcom for next-gen compute"

ketzo — Tue, 07 Apr 2026 01:11:47 +0000

$19B -> $30B annualized revenue in a month?

Feels like the lede is buried here!

New comment by ketzo in "Improving Composer through real-time RL"

ketzo — Sat, 28 Mar 2026 01:18:21 +0000

After seeing the last few releases for GPT and Claude, I’m not sure how anyone (else) is gonna build a durable advantage on proprietary model quality.

The capabilities of the top labs’ models have improved so much in just the last few releases, and I definitely foresee a world where they gate those models away behind 1st-party harnesses/tooling.

New comment by ketzo in "Thoughts on slowing the fuck down"

ketzo — Wed, 25 Mar 2026 16:29:34 +0000

I think the core idea here is a good one.

But in many agent-skeptical pieces, I keep seeing this specific sentiment that “agent-written code is not production-ready,” and that just feels… wrong!

It’s just completely insane to me to look at the output of Claude code or Codex with frontier models and say “no, nothing that comes out of this can go straight to prod — I need to review every line.”

Yes, there are still issues, and yes, keeping mental context of your codebase’s architecture is critical, but I’m sorry, it just feels borderline archaic to pretend we’re gonna live in a world where these agents have to have a human poring over every single line they commit.

New comment by ketzo in "Publish on your own site, syndicate elsewhere"

ketzo — Sat, 03 Jan 2026 06:07:47 +0000

if you're cool just writing markdown files, I really like Astro for self-hosting static content.

New comment by ketzo in "ManusAI Joins Meta"

ketzo — Tue, 30 Dec 2025 00:21:58 +0000

Meta has shown a willingness to offer 9-digit pay packages to individual researchers. Even if they completely scrap the product, an acquihire of even a handful of Manus' top engineers/scientists here is totally in line with that kind of cash.

New comment by ketzo in "Software engineers should be a little bit cynical"

ketzo — Mon, 29 Dec 2025 17:34:22 +0000

Yes, and some people are still happier there!

Different people can have wildly different expectations for a work environment, and wildly different tolerances of social discomfort.

New comment by ketzo in "Trevor Milton's Nikola case dropped by SEC following Trump pardon"

ketzo — Fri, 19 Sep 2025 21:41:41 +0000

But pressuring the SEC to drop the civil claims does!

https://www.nytimes.com/2025/09/19/us/politics/sec-trump-cle...

Building software on top of an LLM is hard, but not that hard

ketzo — Fri, 22 Aug 2025 14:09:14 +0000

Article URL: https://reedtaylorbarnes.com/blog/building-with-llms/

Comments URL: https://news.ycombinator.com/item?id=44984906

Points: 8

# Comments: 0

New comment by ketzo in "How we exploited CodeRabbit: From simple PR to RCE and write access on 1M repos"

ketzo — Tue, 19 Aug 2025 16:47:12 +0000

> While running the exploit, CodeRabbit would still review our pull request and post a comment on the GitHub PR saying that it detected a critical security risk, yet the application would happily execute our code because it wouldn’t understand that this was actually running on their production system.

What a bizarre world we're living in, where computers can talk about how they're being hacked while it's happening.

Also, this is pretty worrisome:

> Being quick to respond and remediate, as the CodeRabbit team was, is a critical part of addressing vulnerabilities in modern, fast-moving environments. Other vendors we contacted never responded at all, and their products are still vulnerable. [emphasis mine]

Props to the CodeRabbit team, and, uh, watch yourself out there otherwise!

New comment by ketzo in "Claude Code weekly rate limits"

ketzo — Mon, 28 Jul 2025 20:53:01 +0000

What does your Claude code usage look like if you’re getting limited in 30 minutes without running multiple instances? Massive codebase or something?

New comment by ketzo in "Major rule about cooking meat turns out to be wrong"

ketzo — Wed, 23 Jul 2025 23:33:29 +0000

That is indeed exactly what the article says — I’m not certain GP is right on this.

Kenji’s original tests seem to confound this as well: every 2.5min of slicing produces steadily less juice, despite the fact that the steak’s internal temp should be rising for some of that time.

New comment by ketzo in "Coding with LLMs in the summer of 2025 – an update"

ketzo — Sun, 20 Jul 2025 21:40:48 +0000

In what ways is that better for you than using eg Claude? Aren’t you then just “locked in” to having a cloud provider which offers those models cheaply?

New comment by ketzo in "XAI seeks up to $200B valuation in next fundraising"

ketzo — Sat, 12 Jul 2025 17:30:36 +0000

I mean — the person you’re describing is just a ChatGPT user and essentially nothing else, though, right?

It explains OpenAI’s valuation but no one else

New comment by ketzo in "Writing documentation for AI: best practices"

ketzo — Wed, 18 Jun 2025 22:42:30 +0000

A really effective prompt is created by developing an accurate “mental model” of the model, understanding what tools it does and doesn’t have access to, what gives it effective direction and what leads it astray

Otherwise known as empathy

New comment by ketzo in "Waymo's market share in San Francisco exceeds Lyft's"

ketzo — Sat, 14 Jun 2025 19:22:59 +0000

They’re probably comparing to taxis, where you can pay in cash.

New comment by ketzo in "Cursor goes rogue in YOLO mode, deletes itself and everything else"

ketzo — Thu, 12 Jun 2025 20:08:42 +0000

Completely unsourced and the site is run by a marketing/PR/growth consultancy.

Between that and the utter lack of detail, feels like not worthy of HN front page.

New comment by ketzo in "You can now legally walk with drinks on SF's Valencia St"

ketzo — Thu, 12 Jun 2025 16:16:13 +0000

“No enforcement” means people who don’t care about breaking rules will do it in brown bags

“Officially allowed and advertised” means businesses will specifically cater to people with money who will come specifically to do it

New comment by ketzo in "Chatbots are replacing Google's search, devastating traffic for some publishers"

ketzo — Wed, 11 Jun 2025 01:33:10 +0000

Then what explains people doing millions of web searches on perplexity/chatgpt/claude?

New comment by ketzo in "Launch HN: Chonkie (YC X25) – Open-Source Library for Advanced Chunking"

ketzo — Mon, 09 Jun 2025 21:20:54 +0000

I’m building out a side project where I need to ingest + chunk a lot of HTML — wrote my own(terrible) hunker naively thinking that would be easy :’)

Definitely gonna give this a try!

New comment by ketzo in "Gemini-2.5-pro-preview-06-05"

ketzo — Thu, 05 Jun 2025 21:16:55 +0000

People said much the same thing about Apple for decades, and they’re a $3T company; not a bad thing to have fans.

Plus, it’s a consumer product; it doesn’t matter if people are “presenting them as leaders”, it matters if hundreds of millions of totally average people will open their computers and use the product. OpenAI has that.