eluru

The musk lied? But the musk never lies! He is an unlier!... An unlier....

is it good now? last year claude GUI was awful, lots of bugs and straight out missing a lot of features

agreed, gets some mid range hardware, some click installing agents with descent customisability, and im talking boring customisability like 'help me plan what to buy this month for my home' kind of tasks. Thats what we are going towards

It will eventually blow up of course but it wont be anything really expectacular, a bunch of larpers will be talking about giant loses for CEOs and surely, hopefully anthropic, all while it doesnt have a big effect on the people that know little about all of this. But still, nothing will be back to how it was, ever

Before reading it i was sure this was going to be about how the PHP creator warned everyone hes language was for blogging, then we had an apocalipse

As obvious as they sound i havent tought about those points before, they do make sense

I studies for some descent while with the objective of using unreal engine, then i found out everyone was just using blue prints so not even them liked CPP

is it 'cognitive surrender' (such a phrase) to use a wiki instead of going to the library? to use your kitchen instead of a fireplace? to hire an editor to check your grammar? to use a calculator, to use linting tools, a dictionary, a copy machine....?

no, i think its not

with this i agree whole heartedly, i can tolerate clanker code in exchange of the amount of value it can generate after heavy polishing, but good writing is something AI is leagues behind, so far back that is even making human writing worse by imitation. Use it for grammar, use it for punctuation, never let the clankers write by themselves and call it a day

ooooof trying to define art, lets call socrates

Then i have no issues being sunned by society, such a double faced bunch of folks

If you think coding is solved you dont know how AI applies patterns, or you dont know about coding patterns at all

Im doing this, against my will i preffered an anchored approach but well the thing is i work for a rich guy, like most of us, i dont care the thing has 'money worth' i only care the rich guy gives me a fraction of the money we produce.

But still, if the thing is really bad it just makes my work harder so im trying to keep it stable, i am still reading the core of the system as much as i can, the agentic pipeline in this case. I have different reviewers working, custom company model, claude, codex they run in different stages of the projects like for SOLID, for linting, thats what we build the review agents for. I check the architecture and design documents throughly before starting, then the AI creates documents that the AI will consume and i check the details didnt changed, the same if you need example proof of concepts, like some inherited approach from the anchored spec driven times. At this point reading every line is not possible, not even worth it to discuss it at company level its not happening, so these kind of things are your safety net now so if anyone has other strats please do share them i think we all need them.

its like the seventh time they solved code, do you think its a good solution this time? i want to retire and paint waifus already

I dont want someone elses choices making my papperwork even slower and im sure most would agree, AI wont take charge of this but society? certainly will

i wonder why dont we have a better pipeline for research. for example ask opus to do some research, then have some hook configured with Haiku, JEV, anything that makes more sense really, only job is ti check the sources are real. you can keep adding into this, of course it can get too big, of course it will still fail, but it will still be much better than the current state of things. It seems to be a low hanging fruit with a huge value that no one has taken.

Having children should not be something life throws at you, if that ends u happening the bast majority of cases is still your responsability to be there, not to put a clanker in place

it was as well designed as the nipples on a man

as a student i remmeber ikept getting my questions removed even after trying to follow every rule. this one time i decided i will use their top questions as a template just to test it, so i did i made sure it was a new question, following each rule

It was also deleted, die already stack overflow

it does not

I like tech

as long as im working for a rich guys company i will be the 'just pay me' dude

my money is still on nuclear but i would be happy to be wrong

Nothing to excuse because thats not what i am asking humans to do, i will never in my life, and i mean it i would rather a clanker kills me, accept a tool telling me what if "feels (what a joke) is correct. i suppose you are a human so no issue there, if you are a clanker, get out of society talk

sadly the only one they kind of explain, open AI is mysterious and cold like sasuke

1. some bad hack for the switch2 took 2 weeks of non stop work for an AI, so most certainly this was expensive.

2. most probably no, the AI doesnt rest and its very very fast.

3. also no, they are doing this for aura farming which then will result in more money for them, the money will dry as soon as this stops working.

stack overflow worthy levels of ego

Another nail in the P not equal NP theory, imagine if AI ends up destroying encrypting lol

we dont have a lot of hoices in south america and he is top notch

found the shareholder