Hacker News: prodigycorp

New comment by prodigycorp in "How Claude Code works in large codebases"

prodigycorp — Fri, 15 May 2026 06:55:31 +0000

Perhaps, but I'm commenting on a blog post called "How Claude Code works in large codebases". That's an interesting question to me. I had hoped there was a more interesting answer.

New comment by prodigycorp in "How Claude Code works in large codebases"

prodigycorp — Fri, 15 May 2026 06:38:49 +0000

My complaint is about how there's not enough information in the blog post. The title of the post is "How Claude Code works in large codebases". 1521 of 18135 characters is dedicated to expanding on the premise of the title.

My criticism is fair. This is not an engineering blog post, it's purely marketing.

New comment by prodigycorp in "How Claude Code works in large codebases"

prodigycorp — Fri, 15 May 2026 05:52:41 +0000

This is really a zero information blog post. I want to know how they use the LSP to improve their understanding of the code base. Would be great if it was open source for us to review.

A post like this should be providing people with some reassurance about Claude's ability to understand code at a large scale. It's mostly fluff.

Edit: so I did some googling to dig around for thoughts on LSP performance and integration. the author of bun has a tweet about saying that they are a big drag on performance for no real gain and virtually all of the replies agree. Anyone else have any experience/thoughts?

https://xcancel.com/jarredsumner/status/2017704989540684176

New comment by prodigycorp in "Googlebook"

prodigycorp — Wed, 13 May 2026 04:36:49 +0000

alphabook

New comment by prodigycorp in "Gmail registration now requires scanning a QR code and sending a text message"

prodigycorp — Mon, 11 May 2026 17:14:36 +0000

I hit both a google QR captcha and traditional captcha today. They're phasing it in.

New comment by prodigycorp in "Canvas online again as ShinyHunters threatens to leak schools’ data"

prodigycorp — Fri, 08 May 2026 01:10:39 +0000

Ok, so we treat it as an act of war. Now what? Attack North Korea? Great, the entire city of Seoul gets shelled within five minutes of your attack and hundreds of thousands of innocent people die.

It's very easy to play with lives that aren't yours.

New comment by prodigycorp in "Accelerating Gemma 4: faster inference with multi-token prediction drafters"

prodigycorp — Wed, 06 May 2026 04:12:35 +0000

This used to be the case, but the changes last month have rendered the Gemini Pro plan completely unusable.

New comment by prodigycorp in "Accelerating Gemma 4: faster inference with multi-token prediction drafters"

prodigycorp — Wed, 06 May 2026 04:11:55 +0000

I think you can see this one of two ways: you could also consider it a miracle that the qwen models are able to perform so well when being trained on inefficient wrapper code data.

New comment by prodigycorp in "Show HN: I built a tool that helps predict HN front page success"

prodigycorp — Sun, 03 May 2026 12:22:16 +0000

Idk how to make it more obvious that you’ve used a vote ring than 15 votes in ten minutes.

New comment by prodigycorp in "Claude Code refuses requests or charges extra if your commits mention "OpenClaw""

prodigycorp — Thu, 30 Apr 2026 16:28:50 +0000

I hereby propose we rename the HN frontpage to "Claude Customer Support"

New comment by prodigycorp in "Mistral Medium 3.5"

prodigycorp — Wed, 29 Apr 2026 17:23:31 +0000

i run qwen 3.6. you need to drink some settle down juice.

New comment by prodigycorp in "Tell HN: Claude 4.7 is ignoring stop hooks"

prodigycorp — Sat, 25 Apr 2026 08:05:23 +0000

Am I the only one who thinks that your stop hook is written extremely poorly? Not only that, but you're writing to the LLM like an abusive human. No wonder it wants to go home.

New comment by prodigycorp in "Website streamed live directly from a model"

prodigycorp — Thu, 23 Apr 2026 04:48:39 +0000

Thank you for sharing this. Not often do you get projects that expand your imagination about what we can do with these models.

New comment by prodigycorp in "Qwen3.6-35B-A3B on my laptop drew me a better pelican than Claude Opus 4.7"

prodigycorp — Thu, 16 Apr 2026 19:47:08 +0000

To me the opus flamingo is waaaay better than the qwen one. qwen has the better pelican, though.

New comment by prodigycorp in "DIY Soft Drinks"

prodigycorp — Mon, 13 Apr 2026 11:07:48 +0000

He's contributed to improving trust on this forum. And idk if you've ever gotten commercial samples before but he's right, the amount they give you is immaterial to hurting them and can be material to you.

Also, he said that he's somehow stumbled into somehow having a commercial bottling license. If him, why not us?

New comment by prodigycorp in "Cirrus Labs to join OpenAI"

prodigycorp — Sat, 11 Apr 2026 16:53:01 +0000

I don't think people have been keeping track but OpenAI has been hiring a murderer's row of developers for their Codex team.

New comment by prodigycorp in "Muse Spark: Scaling towards personal superintelligence"

prodigycorp — Thu, 09 Apr 2026 05:01:36 +0000

It was from a techmeme ride home podcast where the host discussed "sources at the company said". I don't remember which day's episode it was.

New comment by prodigycorp in "Muse Spark: Scaling towards personal superintelligence"

prodigycorp — Wed, 08 Apr 2026 17:46:03 +0000

Nah I remember how disgusted I felt trying llama 4 maverick and scout. They were both DOA.. couldn't even beat much smaller local models.

New comment by prodigycorp in "Muse Spark: Scaling towards personal superintelligence"

prodigycorp — Wed, 08 Apr 2026 17:31:52 +0000

the models were objectively horrible

New comment by prodigycorp in "Muse Spark: Scaling towards personal superintelligence"

prodigycorp — Wed, 08 Apr 2026 17:19:04 +0000

Comments trashing this are rightly correct skeptics who remember the benchmaxxing of llama 4. This model was out in the woods as early as like a couple months ago but they didn't release it because it was at gemini 2.5 pro levels.