Hacker News: denimnerd42

New comment by denimnerd42 in "Predicting the 2026 Bristol Bay and Kodiak Salmon Runs"

denimnerd42 — Sun, 24 May 2026 17:15:09 +0000

I sport fished Kodiak for halibut and salmon in 2009. what a crazy place to fish. the abundance of fish was incredible

New comment by denimnerd42 in "Colorado Amended SB051 (Age Verification Bill) to Exclude Open Source Projects"

denimnerd42 — Wed, 20 May 2026 22:37:40 +0000

hopefully if each state starts crafting dumb laws like this they all get banned via commerce clause due to infeasibility of compliance

New comment by denimnerd42 in "SpaceX S-1"

denimnerd42 — Wed, 20 May 2026 22:25:29 +0000

a GB300 rack is like 5-6 million so seems a bit low.

New comment by denimnerd42 in "Filing the corners off my MacBooks"

denimnerd42 — Tue, 14 Apr 2026 15:25:00 +0000

yeah. gonna be a huge mess so I havent

New comment by denimnerd42 in "Filing the corners off my MacBooks"

denimnerd42 — Fri, 10 Apr 2026 22:58:32 +0000

I hate those sharp edges. I've contemplated taking a router with a carbide roundover to mine many times.

New comment by denimnerd42 in "OpenAI's new $100 tier targets developers hitting Codex limits"

denimnerd42 — Fri, 10 Apr 2026 22:50:02 +0000

We don't spend that much money every day but here's the gist: We have a distributed system that has several components that don't meet the performance requirements of the next uplift we need to do. We need to carefully consider the tradeoffs of things like how to shard a few of the databases, how to rearchitect the ETL flow that comes off the system and is used for analysis. We think of a few approaches and then we get the coding assistants to blast through the end to end development of each approach discovering all the known unknowns and unknown unknowns along the way. Then we can load test each method, profile them, analyze them manually and with the LLM. Then we can pick the solution and take another shot at implementing it with the coding agent, but more carefully and with more oversight with all the things we learned.

We don't hit those high numbers every day. An average day is $50-100 max.

As far as home projects. Something like write a GUI desktop or phone application from scratch. The LLM has to reference a lot of code and API docs to figure out what to do and spends a lot of time thinking while debugging. It gets expensive :/

New comment by denimnerd42 in "OpenAI's new $100 tier targets developers hitting Codex limits"

denimnerd42 — Fri, 10 Apr 2026 21:38:26 +0000

I have at least walked 20 miles before in my life. I've never written anything with as much breadth in 20 years of coding until I started using these tools. I also have quite a deep backlog from trying.

New comment by denimnerd42 in "OpenAI's new $100 tier targets developers hitting Codex limits"

denimnerd42 — Fri, 10 Apr 2026 19:11:35 +0000

That’s what Im considering.

New comment by denimnerd42 in "OpenAI's new $100 tier targets developers hitting Codex limits"

denimnerd42 — Fri, 10 Apr 2026 19:08:26 +0000

When I sit down and dial in on a serious project at work I easily spend $500-1000+ day of API usage. At home I just hit the limit and give up / cancel my sub.

Wish I could just go all out one weekend a month. I hardly code outside of work but sometimes there’s a project I have an itch for.

New comment by denimnerd42 in "Autonomy Is Real Now"

denimnerd42 — Fri, 10 Apr 2026 18:55:16 +0000

may open up other opportunities due to people being more mobile. more commerce activity in general. I heavily dislike having to find parking or hiring a non waymo ride.

New comment by denimnerd42 in "Claude Code is unusable for complex engineering tasks with the Feb updates"

denimnerd42 — Mon, 06 Apr 2026 16:15:56 +0000

this prompt is actually in claude cli. it says something like implement simplest solution. dont over abstract. On my phone but I saw an article mention this in the leak analysis.

New comment by denimnerd42 in "Claude Code's source code has been leaked via a map file in their NPM registry"

denimnerd42 — Tue, 31 Mar 2026 12:46:12 +0000

all these flags are findable by pointing claude at the binary and asking it to find festure flags.

New comment by denimnerd42 in "Why I forked httpx"

denimnerd42 — Wed, 25 Mar 2026 17:37:51 +0000

I feel like Java does it the best. Golang didn't start with generics so it's a bit odd IMO.

New comment by denimnerd42 in "Why I forked httpx"

denimnerd42 — Wed, 25 Mar 2026 15:05:25 +0000

the batteries included approach is the stdlib that can do everything. turns out it’s hard to maintain and make good.

New comment by denimnerd42 in "What Claude Code chooses"

denimnerd42 — Fri, 27 Feb 2026 16:32:17 +0000

reinforcement learning is all code that was created by coding gig workers through scale ai and similar. I cannot believe it would be very good.

New comment by denimnerd42 in "What Claude Code chooses"

denimnerd42 — Fri, 27 Feb 2026 16:28:11 +0000

creating plans in claude and asking chatgpt via api to review loop was my strategy this week. I'm not a big fan of codex as a coding harness because it seems to just give up quite easily where claude will search the problem space and try things but I think gpt does a much better job of poking holes and asking clarifying questions when prompted.

New comment by denimnerd42 in "Sub-$200 Lidar could reshuffle auto sensor economics"

denimnerd42 — Mon, 23 Feb 2026 18:57:28 +0000

did you see this, they can build a simulator from sv images. https://waymo.com/blog/2026/02/the-waymo-world-model-a-new-f... even the lidar part

New comment by denimnerd42 in "How I use Claude Code: Separation of planning and execution"

denimnerd42 — Sun, 22 Feb 2026 03:07:57 +0000

yeah i experienced this the other day when asking claude code to build an http proxy using an afsk modem software to communicate over the computers sound card. it had an absolute fit tuning the system and would loop for hours trying and doubling back. eventually after some change in prompt direction to think more deeply and test more comprehensively it figured it out. i certainly had no idea how to build a afsk modem.

New comment by denimnerd42 in "Anthropic officially bans using subscription auth for third party use"

denimnerd42 — Thu, 19 Feb 2026 06:41:30 +0000

GB300 NVL72 is 50% more expensive than GB200 I've heard.

New comment by denimnerd42 in "Students Are Finding New Ways to Cheat on the SAT"

denimnerd42 — Thu, 29 Jan 2026 22:31:22 +0000

If the test is taken on personal laptops it's almost impossible to stop cheating. You can easily take video capture and send it out via 5g modem on a completely separate computer hidden inside of the laptop. Then you can receive answers back in very discreet ways like nearly imperceptible LEDs.

Same reason DRM-data rights management or DLP-data loss protection technologies are rather pointless against determined attackers. Anything that is permitted to be viewed can be copied.