not_that_d

At work we had copilot. It said "the diff is too big to review"

I am too stupid to know if this is really smart or really dumb.

I don't think your friend understands Large LANGUAGE models.

The amount of consultants that are very known and have large presence on developer communities and give a lot of talks and have no idea how to approach real world problems is impressive.

Asking as a non American. Why would this matter to me? Why should I care about this?

Yeah, no. I canceled my subscription yesterday. It is Claude is unusable right now.

You know, after a while this excuse is not valid anymore.

That depends on what you call "Think" we made the interface of LLM of the second "L", Language. And it can hack our perspective of the thing.

> I don't understand how LLMs actually work...

Plot twist, they don't either. They just throw more hardware and try things up until something sticks.

While true, it influences a lot in the EU

But why? You can get a Kindle with ads, jailbreak it and having Bezos pay the halb of your Device

To be honest, in my decades working in this, I have never ever saw a Manager that was a good Developer. Maybe it is just my luck.

Seems like we are ready heading to what the OpenAI CEO wanted "intelligence just available thru a subscription"

Does ICE needs something?

I am now using LLM at 100% at work and producing faster code, while I keep growing my regular skills privately in "old way".

Why? Because when the bubble burst and the companies (including mine) can not pay the 400% price increase and go bankrupt, then I still have keep my brain active and still can do stuff without or less tokens.

What is with the amount of comments talking about other countries in Europe "Doing the same"?

I would like to see a proof of this happening in Europa.

The funny thing is, when I got a lead position in my job, I just to do real detailed ticket descriptions, going into technical considerations and possible cross domain problems. I did it for the juniors - and to be honest - for my self, since I know if I took that ticket, from that moment to the moment I put some code down I could just forget stuff.

This was pushed back hard by management because it "took too much time to create a ticket". I fought it for some months but at the end I stopped and also really lose the ability and patience of do that. Juniors suffered, implementation took more time. Time passed.

Now, I am supposed to do the exact same thing, but even better and for yesterday.

What the post fails to understand is that a lot of the "top" people if big companies just doesn't understand the regular user because, well, they do not live a life like the regular users.

Besides my other response, it can also be I am not smart enough for it.

The code is quite easy to follow to be honest, we have documented a lot of stuff and segmented functionality into libraries that follow an app/feature/models pattern. Almost every service we have, has unit tests explicitly describing what the public api is doing or supposed to do on several scenarios, we never test implementation details.

Given it to new people of course carry questions, but most of them (juniors) could just follow the code given an entry point for that task, this from BE to FE.

I use the github copilot premium models available.

> I routinely make an implementation plan with Claude and then step away for 15 mins while it spins - the results aren’t perfect but fixing that remaining 10% is better than writing 100% of it myself.

I have to be honest, I just did this two times and the amount of code that needed to be fixed, and the mental overload to find open bugs was much more than just guide the LLM on every step. But this was a couple of months ago.

What is "Vibe testing"?

I don't understand people criticizing this. Didn't they read the article? The new Suzi stuff doesn't want to replace Zigbee, and the new zigbee version is backwards compatible.

What is the pain there?

As an ex audio engineer, I would say that the war ended and loudness won.

I am living this but the CEOs of my company are also "active" programmers.

Even when I already hear from them that "it helps them in language they do not know" (which is also my experience) I get frown upon if on meetings I do not say that I am "Actively using AI to GENERATE whole files of code".

I use AI as rubber duck, generate repetitive code or support me when going into an new language or technology, but as soon as I understand it, most of the code given for complete, non hobby, enterprise level projects contains either inefficient code or just plain mistakes which takes me ages to fix for new technologies.

I wonder if they will dedicate resources to help the development of their open source tools?

I have seen really inept people given manager positions because they were out going and then crash after six months in the position and expecting that we fix all the management issues for some reason.

Honestly, I have no energy to be as social as the work life needs me to be, maybe that is ok. Maybe no.

For me is not so. It makes me way faster in languages that I don't know, but makes me slower on the ones I know because a lot of times, it creates code that will fail eventually.

Then I need to expend extra time following everything it did so I can "fix" the problem.