veber-alex

The value of these models is that you can run them on your own hardware.

A company can buy a NVIDIA B300 and serve it's developers in house with unlimited tokens.

Nobody cares about this anymore.

On Windows you have 20 different ways to write native apps that all look different.

On Linux you have Qt/GTK and god knows what else.

Only macOS is somewhat consistent although with Liquid Ass it's also getting worse.

ChatGPT works ok for me but Whatsapp consumes 1000% cpu after the mac wakes up after sleep.

I swear a few years ago shit like this didn't happen on macOS.

Yes it's my main AI thing.

It has access to all top models, great IDE integration and their AI based autocomplete is still unbeaten.

I have no desire to use a TUI, feels like a downgrade to me.

Don't bother, you will just be downvoted to oblivion.

Assume every post here is automatically anti something and don't engage. Your mental health isn't worth it.

It's fast. All websites work. I like how it handles tabs and tab groups. uBO Lite is good enough for me.

Yep.

One time my manager did a hour long lecture for our team on how personal growth is important and that we all should expand our horizons and learn new stuff.

When I tried to reserve 2 hours A WEEK for studying tasks I got push back that I should do it on my own time. It was a complete joke.

Every developer who writes code for a living should get an AI subscription from work and not have to pay for it himself.

Vera doesn't use soldered memory, it uses SOCAMM2.

You are doing a 100 searches a day on avarage? Is your job to search for random stuff on the internet?

You are not the only one.

Huh? the github page of pretty much anything is always in the top 5 results for me.

Spotlight search is completely broken.

If I type "sa" the first result is Safari but if I type "safa" I get "Adguard for Safari.app".

In what world does this make sense?

Seriously. It's one thing to use AI to write code but spamming machine generated garbage when talking to another person is just rude.

Looks like AI slop

https://github.com/PerryTS/perry/issues/139

Double check what the AI tells you. Apply common sense instead of blindly trusting everything. If it's something technical in nature try to verify and test it.

I treat AI as any other information I see online with the added value that it's customized exactly to my needs and it works pretty well for me.

Right because without AI everything you read on the internet is 100% true and correct.

Learn how to use AI properly just like any tool and you can benefit.

The main complaint about Cursor I see online is that it's expensive.

Otherwise if you are looking for and IDE first approach with great AI integration it's the best product out there. I prefer it over CC/Codex.

ffs can we stop talking about that number and site already.

It treats any service being down as the entire platform being down which is nonsense.

It's just lying with statistics.

I actually noticed this too. GPT 5.5 is much more "hands on" with calling tools to debug issues and verify results. I did all my tests in Cursor but I don't know if they use a different system prompt for each model.

In my experience benchmarks are pretty meaningless.

Not only is performance dependent on the language and tasks gives but also the prompts used and the expected results.

In my own internal tests it was really hard to judge whether GPT 5.5 or Opus 4.7 is the better model.

They have different styles and it's basically up to preference. There where even times where I gave the win to one model only to think about it more and change my mind.

At the end of the day I think I slightly prefer Opus 4.7.

This is exactly how I feel.

Cursor works just fine for me. I just don't have the incentive to learn a new tool even though I think Zed is cool.

They got sued for downloading pirated books and not for using them for training. Huge difference.

Antropic and OpenAI are used by US businesses and government and they are audited and under contracts.

If it's discovered they trained on data they shouldn't have had it will be the end of their business.

On the other hand, good luck suing a Chinese company.

That's just throwing money away. The performance with large context would have been unusable especially if you need to serve more then a single person.

I did't but that's exactly my point.

Native apps are so poorly optimized that they don't offer any advantage over Electron apps.

Price is set based on what people are willing to pay not based on actual costs.

American companies just take those Chinese models and repackage them for profit like Cursors composer-2.

As if native apps are any better. Books app on my mac takes 400MB without even having a single book open.

I use iTerm2 with tmux CC mode. Works great and gives native tabs and panes.