Mohamed Latreche
1K posts

Mohamed Latreche
@latreche2000
(6*9) + (6+9) = 69 math is beauty.
the milky way galxy Katılım Kasım 2018
1.3K Takip Edilen90 Takipçiler

Claude usage limits are insane
Asked one question and it's already at 75% of the weekly limit.
How is that even possible?
@trq212 Would appreciate any help with this.

English

I see a lot of people suggesting that instead of signing a striker, we should just get a top LW and move Raphinha into a false 9 role. And I understand the logic because he already likes to drift inside and doesn’t really play as a touchline winger anyway.
But a false 9 isn’t just “a winger playing centrally.” The role is about dropping between the lines, pulling center-backs out of position, linking play and creating space for others to attack.
That’s not really Raphinha’s game. He’s much more dangerous as the player attacking the space rather than the one creating it. His biggest strengths are his runs into the box, his movement off others, and arriving in dangerous areas to finish actions.
So moving him to false 9 would probably take away the things that make him most effective in the first place.

English

@GaryMarcus is AI coding really useful or people are using it because it's a trend and have the fear of missing out
English

The last sentence in this abstract is really important, in a way that professional programmers will immediately recognize: the models favored big single files rather than breaking things into modules.
That means that the code these systems write is going to be really hard to maintain.
AI code might get written quickly, but especially in new, complex projects, fixing it will be hell.
Deedy@deedydas
The creators of SWE-Bench just dropped a really simple new benchmark every LLM gets 0% on. ProgramBench asks: can models recreate real executable programs (ffmpeg, SQLite, ripgrep) from scratch with no internet? We are far from saturated on model quality.
English

@lauriewired Comparing LLMs with compilers does not make sense the output of compilers is deterministic
English

There’s a famous Usenet story about a programmer (Mel) who refused higher level abstractions.
It was the late 1950s, and even in that era, Mel was…well today we’d call him a boomer.
Mel only wrote in raw hexadecimal. He didn’t approve of compilers, and refused to use optimizing assemblers.
"You never know where it's going to put things”, he said.
Everyone else in the company was moving on to FORTRAN, and they didn’t understand why Mel was so stubborn about using new tools. He *loved* self-modifying code.
“If a program can’t rewrite its own code”, he asked, “what good is it?”
Mel eventually left the company, and other engineers were tasked with understanding what was left.
Mel’s hand-optimized routines always beat the assemblers; but some of it looked absolutely bizarre.
One engineer took ~2 weeks to understand why there were loops with no exit condition…yet the program worked fine.
I won’t spoil all the details, you should really read it, it’s short. But it’s a fantastic piece on “what defines a real programmer?”…which is becoming increasingly relevant in this vibe-coded era.
I strive to understand computers as deeply as Mel! If we aren’t careful, we’re going to lose the “Mels” of this world to time.
That’s part of why I go so deep in my youtube videos. I hope that younger viewers are genuinely fascinated by the inner workings of our machines, instead of handing everything off to higher abstractions.
solst/ICE of Astarte@IceSolst
Interesting article on treating agent output like compiler output (and why) skiplabs.io/blog/codegen_a…
English

Si se acaba yendo esta temporada le consideráis una leyenda del Barça?
Polymarket Sports@PolymarketSport
🚨OFFICIAL: Robert Lewandowski will leave Barcelona at the end of the season. Per @GuillemBalague
Español

@wagslane I didn't care what they said when they were saying nonsense, and I still don't care when they say based stuff
English

















