Hacker News: throwaway6977

New comment by throwaway6977 in "Claude, change the “Add to Cart” button to blue"

throwaway6977 — Wed, 09 Sep 2026 14:43:56 +0000

It's just a lot faster at hammering it out than me pound for pound, and I can quickly rattle off via voice-to-text exactly what I want much faster than I can type all of the code (especially when across a few different files), in a huge majority of tasks I perform. It's also especially good at debugging by brute force quickly and at scale meaning e.g. it can start desperately bisecting diffs to find the source of a bug 10000% faster than I can.

New comment by throwaway6977 in "How do we stop vibe coding?"

throwaway6977 — Fri, 24 Jul 2026 13:15:21 +0000

Disagree with so many assertions put forth here. You don't _have_ to turn you brain off when coding with an LLM. It's not some intelligence dementor. If your brain turned off while you were vibe coding thats honestly just a you problem and I wish everyone would stop boogeymanning an obvious improvement in the ability to better yourself just because a lot of people don't choose the betterment route.

I've never been more informed or understood more about my code, pipelines, and stack than now- and its 100% due to AI reasoning about my projects, and me making an effort to learn.

Ask HN: Are you more quickly hitting Claude Code limits the past 48-96 hours?

throwaway6977 — Thu, 26 Mar 2026 15:26:48 +0000

Personally, I was not impacted Monday and most of Tuesday. Now since yesterday I cannot run a single prompt without eating my entire 5 hour window. I'm talking an identical prompt on an identical repo state from something I ran Saturday that only spent ~5% usage max then, now eats my entire 5-hour window. Switching to Sonnet doesn't even help...

Comments URL: https://news.ycombinator.com/item?id=47531697

Points: 6

# Comments: 3

New comment by throwaway6977 in "Qwen3.5 Fine-Tuning Guide"

throwaway6977 — Wed, 04 Mar 2026 15:15:27 +0000

I agree- I'm currently trying to learn how I can embed a fine tuned tiny model into my c++ game so it can provide a narrative in prose of certain game-event logs. It needs to be as tiny as possible so it doesn't take resources away from the running game.

New comment by throwaway6977 in "OpenClaw surpasses React to become the most-starred software project on GitHub"

throwaway6977 — Mon, 02 Mar 2026 16:42:14 +0000

Sounds similar to buying a 3D printer hehe

New comment by throwaway6977 in "The chess bot on Delta Air Lines will destroy you (2024) [video]"

throwaway6977 — Mon, 12 Jan 2026 21:12:22 +0000

Chess on M series Macs has the same issue. Even level 1 is easily 2000+ Elo because of the same thing.

New comment by throwaway6977 in "GOG is getting acquired by its original co-founder"

throwaway6977 — Tue, 30 Dec 2025 16:00:21 +0000

GN is a well established, popular and independent consumer hardware reviewer that has only a few peers on par with them in the space. Hardly some "random tech influencer".

New comment by throwaway6977 in "How I learned Vulkan and wrote a small game engine with it (2024)"

throwaway6977 — Sat, 22 Nov 2025 21:13:10 +0000

There is mention of desktop applications in their getting-started docs; it seems well within the intention of the maintainers to me.

https://eliemichel.github.io/LearnWebGPU/introduction.html

> Yeah, why in the world would I use a web API to develop a desktop application?

> Glad you asked, the short answer is:

    Reasonable level of abstraction

    Good performance

    Cross-platform

    Standard enough

    Future-proof

New comment by throwaway6977 in "You should write an agent"

throwaway6977 — Fri, 07 Nov 2025 00:19:02 +0000

You can be your own AI provider.

New comment by throwaway6977 in "I don't want AI agents controlling my laptop"

throwaway6977 — Wed, 10 Sep 2025 13:24:11 +0000

I just spent a lot of yesterday tweaking a docker image with xfce and vs code so I can just let codex go full access mode without too much worry in a throwaway sandbox. The agent runs similarly-namespace-constrained and without sudo. I think it's a relatively safe middleground- do you really think container escape is still a big deal here?

Finally getting this setup also allowed me to very quickly troubleshoot what was breaking my build in the codex cloud hosted container which obviously has even less risk attached.

Now I'm juggling and strategizing branches like coding is an RTS game... and it feels like a super power. It's almost like unlocking an undiscovered tech tree.

New comment by throwaway6977 in "AGI is an engineering problem, not a model training problem"

throwaway6977 — Sun, 24 Aug 2025 00:54:38 +0000

I think that completely discounting the potential of new emergent capabilities at scale undermines this thesis significantly. We don't know until someone tries, and there is compelling evidence that there's still plenty of juice to squeeze out of both scale and engineering.

New comment by throwaway6977 in "Mastercard deflects blame for NSFW games being taken down"

throwaway6977 — Mon, 04 Aug 2025 15:40:14 +0000

What is preventing any of those mentioned card vendors from integrating with FedNow either directly or via some abstractive layer through another entity? I don't understand why the answer would be 'no for these reasons'.

New comment by throwaway6977 in "Interviewing the Interviewer: Questions to Uncover a Company's True Culture"

throwaway6977 — Sat, 17 Aug 2024 12:47:25 +0000

If that's the case perhaps you could, I don't know, state that up front and save everyone some time...

New comment by throwaway6977 in "The 8-bit era: Eight processor designs"

throwaway6977 — Mon, 04 Dec 2023 17:18:51 +0000

Cool link, reply more if you find them!

New comment by throwaway6977 in "Covid's damage lingers in the heart"

throwaway6977 — Tue, 24 Oct 2023 15:23:15 +0000

Hey I just wanna say that I'm really glad that you personally haven't had to go through the hell of cardiovascular/heart damage from this, but you also shouldn't use your anecdote to undermine others' extreme sickness. You are ignorant to experiences not your own.

New comment by throwaway6977 in "Low serotonin levels might explain some Long Covid symptoms, study proposes"

throwaway6977 — Wed, 18 Oct 2023 14:41:53 +0000

You get down voted because there are thousands of people suffering from real physical symptoms of this - like clots and tachycardia - and you are waving away the symptoms as a mental illness.

What a joke; I hope no one ever does that to you.

New comment by throwaway6977 in "Low serotonin levels might explain some Long Covid symptoms, study proposes"

throwaway6977 — Wed, 18 Oct 2023 14:37:06 +0000

This sentiment (which is unfortunately rampant) is incredibly ignorant of the actual disease and infantilizes it's victims. I'd LOVE to see people who espouse this idea- go and do some more research about the disease they clearly don't have, and have not experienced first-hand.

New comment by throwaway6977 in "Mistral 7B"

throwaway6977 — Wed, 11 Oct 2023 16:42:24 +0000

(ha!)

New comment by throwaway6977 in "Two years of Bitcoin in Bukele’s El Salvador"

throwaway6977 — Sat, 02 Sep 2023 13:59:08 +0000

It's actually more like choosing a reliable brand that's been around for years vs. buying a Tesla.

New comment by throwaway6977 in "“But the SEC let us go public” and other flawed arguments in Coinbase's defense"

throwaway6977 — Tue, 13 Jun 2023 12:43:22 +0000

I'm sorry, but I'm not willing to answer that for you in a binding way.