coopykins

Something similar is happening in my region after the flood that happened two years ago: The alarm was raised late; Now, even mild rain is triggering an alert.

Guess whats the consequence of that? Less and less people pay attention to the alerts.

It's become a real risk to take a train in Spain. Two severe accidents in the same year on what's typically considered the safest transport method.

I can't remember the last time I read good news related to my country.

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.

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.

Surprising how cheap Sol 6 was.

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.

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.

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

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

Anthropic is vibe running the company.

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

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

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.

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

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

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.

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.

I gotta try this!

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.

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

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.

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.

This is a good guide on how to use Claude code. My perspective (from an early adopter of LLMs for coding) is similar. Though, open code has a lot of potential as well. So I'm happy that Claude Code is not the only option. But a key aspect imo is that, using these tools is also a skill; And there's a lot of knowledge involved in making something good with the assistance of Claude code vs doing slop. Specially as soon as you deviate from a very basic application / work in a larger repo with multiple people. There's a layer of context that these tools don't quite have, and it's very difficult to consistently provide them with. I can see this being less the case as context windows and the reliability of larger context retrieval is solved.

Funny thing, I was just looking for such a tool last week!

Vs code became unusable on a not so big monorepo on a MacBook Pro M4, which is concerning. Zed has been much smoother, even there are a couple of extensions or features that I miss.

The only reason I keep my home PC with windows still is that I use it mainly to play games and some have anti-cheat systems that are not compatible with Linux. But I play those games less and less the older I get, I play mostly older games / emulators. I see it very likely that I won't install whatever comes after Windows 11 and at that point I might move over to Linux for good.

Surprised to see a lot of mentions to Children of Time, a book I picked picked up on a whim in a local Bookshop (something I probably hanger done in 5 years)

Maybe this is a nice chance to ask, would you move from Gitlab to Github? I would say no, but some people in my org are proposing it, it seems to me simply because the integration it has with AI tools, but my experience has been worse in Github than with Gitlab.

It's the first VR device I consider buying.

How does this compare to using the recently released chrome mcp?