Hacker News: coopykins

New comment by coopykins in "Pi 1.0"

coopykins — Fri, 02 Oct 2026 06:37:40 +0000

Codex generally lets you use the subscription with 3rd party agents / harnesses. ON the PI 1.0 you can directly use the openAI log in to hook up your account, so it should be pretty straight forward. I haven't tried myself yet.

New comment by coopykins in "GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price"

coopykins — Wed, 30 Sep 2026 06:17:07 +0000

I had the feeling that GPT 6 Sol was actually GTP 6 Terra, it didn't felt as good as Sol, and the benchmarks also showed it was a bit worse than the previous Sol release.

Now this feels like its the actual Sol 6 that was meant to be.

New comment by coopykins in "Sonnet 5.5"

coopykins — Tue, 29 Sep 2026 07:51:04 +0000

Surprising how cheap Sol 6 was.

New comment by coopykins in "Spain orders blocks on Archive.today and its mirrors"

coopykins — Mon, 21 Sep 2026 07:46:55 +0000

Every single day, I find another reason to be ashamed of my country. We're on a speedrun to turn a modern democratic country into a corrupt shithole in every way imaginable.

New comment by coopykins in "DeepSeek launching v4.1 flash cheaper and more capable than v4 pro"

coopykins — Wed, 09 Sep 2026 14:14:56 +0000

I really enjoy using V4 Flash for digging though data and such. Its a very good model for the price. Looking forward to this one.

New comment by coopykins in "We made Grok 4.5, GPT-5.5, and Claude build the same apps"

coopykins — Thu, 09 Jul 2026 06:19:08 +0000

Impressive, specially the amount of models used for the comparison.

New comment by coopykins in "Show HN: Yamanote.fun – A complete soundscape for Tokyo's Yamanote line"

coopykins — Thu, 09 Jul 2026 06:08:52 +0000

Please, add an option to make the 'travel' between stations longer to give a vibe of an actual train trip!

New comment by coopykins in "Claude Code to be removed from Anthropic's Pro plan?"

coopykins — Wed, 22 Apr 2026 10:53:14 +0000

Anthropic is vibe running the company.

New comment by coopykins in "An AI Vibe Coding Horror Story"

coopykins — Tue, 14 Apr 2026 10:33:38 +0000

I interviewed some years ago for an AI related startup. After looking at the live product, first thing I see is their prod dB credentials and openAI api key publicly send in some requests... Bad actors will be having a lot of fun these days

New comment by coopykins in "The Miller Principle (2007)"

coopykins — Sun, 12 Apr 2026 10:49:34 +0000

It's one of the main things I learned when working as tech support and I talked with users all day. Nobody reads anything.

New comment by coopykins in "Cursor 3"

coopykins — Fri, 03 Apr 2026 16:39:25 +0000

The reason I used cursor, other than it being paid by my employer, is that it had a pretty good integration between IDE and the agent workflow.

If I want to mostly direct 1 or more agents I go straight to claude code (codex at home.)

But I still want to have a IDE at the end of the day, I do look and review the code. I still need to direct it to fix some things it doesn't do properly and I dont feel like giving up my understanding of the system I work with (despite what the vibe people say) I don't think it will lead to good outcomes or any benefit in the name of speed.

So for me this direction goes against what I find useful in cursor, and entirely seems to look out for the the 10+ agents crowd. Which makes sense, these are the guys spending +200 $ subscriptions and so on. I'll go back to Zed + CC or Codex.

By the way their new interface looks just like the Codex App.

New comment by coopykins in "I put all 8,642 Spanish laws in Git – every reform is a commit"

coopykins — Sat, 28 Mar 2026 12:26:37 +0000

Hey, very nice! Seems like a great way to have LLMs answer questions about the laws more reliably.

New comment by coopykins in "Shell Tricks That Make Life Easier (and Save Your Sanity)"

coopykins — Thu, 26 Mar 2026 13:45:14 +0000

My favourite QoL improvement to any shell I use is to improve the history function(Ctlr+R)I personally like https://github.com/cantino/mcfly

New comment by coopykins in "Get Shit Done: A meta-prompting, context engineering and spec-driven dev system"

coopykins — Wed, 18 Mar 2026 09:06:12 +0000

There are so many of these "meta" frameworks going around. I have yet to see one that proves in any meaningful way they improve anything. I have a hard time believing they accomplish anything other than burn tokens and poison the context window with too much information. What works best IME is keeping things simple, clear and only providing the essential information for the task at hand, and iterating in manageable slices, rather than trying to one-shot complex tasks. Just Plan, Code and Verify, simple as that.

New comment by coopykins in "Writers and Their Day Jobs"

coopykins — Thu, 26 Feb 2026 07:33:13 +0000

Most of the jobs listed seem something you can do on autopilot, while your mind is doing something else, which would make sense for creative minds.

New comment by coopykins in "EDuke32 – Duke Nukem 3D (Open-Source)"

coopykins — Sun, 22 Feb 2026 08:23:46 +0000

I gotta try this!

New comment by coopykins in "Discord will require a face scan or ID for full access next month"

coopykins — Tue, 10 Feb 2026 08:29:47 +0000

I think discord has been terrible for the internet. A lot of open information has become gated. And now it's gated behind a platform that many of us are not willing to use anymore. Let's hope this pushes out people and communities back to forums and such, but in reality other platform will take over.

New comment by coopykins in "PlayStation 2 Recompilation Project Is Absolutely Incredible"

coopykins — Fri, 30 Jan 2026 07:41:27 +0000

My all time favorite console. I keep coming back to it. This to me is a fantastic way to preserve gaming history.

New comment by coopykins in "There is an AI code review bubble"

coopykins — Tue, 27 Jan 2026 07:45:25 +0000

Same here, tested a bunch and cursor has been given little noise and usually decent suggestions. In this case its on a react app, so other projects might not find it as good.

New comment by coopykins in "Your brain on ChatGPT: Accumulation of cognitive debt when using an AI assistant"

coopykins — Thu, 22 Jan 2026 07:51:29 +0000

When I have to put together a quick fix. I reach out to Claude Code these days. I know I can give it the specifics and, Im my recent experience, it will find the issue and propose a fix. Now, I have two options: I can trust it or I can dig in myself and understand why it's happening myself. I sacrifice gaining knowledge for time. I often choose the later, and put my time in areas I think are more important than this, but I'm aware of it.

If you give up your hands-on interaction with a system, you will lose your insight about it.

When you build an application yourself, you know every part of it. When you vibe code, trying to debug something in there is a black box of code you've never seen before.

That is one of the concerns I have when people suggest that LLMs are great for learning. I think the opposite, they're great for skipping 'learning' and just get the results. Learning comes from doing the grunt work.

I use LLMs to find stuff often, when I'm researching or I need to write an ADR, but I do the writing myself, because otherwise it's easy to fall into the trap of thinking that you know what the 'LLM' is talking about, when in fact you are clueless about it. I find it harder to write about something I'm not familiar with, and then I know I have to look more into it.