The most important thing to consider, especially in our new times.
Replying to @yacineMTB
From Elon, I learned that most problems are actually totally fake if instead you decided to have courage
3
55
Yes because some new and valuable cars have keyless entry and you can’t turn them on yet, read what the fucking game tells you. You need the key cloner.
YOU CANT STEAL CARS IN GTA VI🚗
You can enter the car but it won’t move
This is insane!
Readers added context they thought people might want to know
You can steal cars in GTA VI from the start by carjacking or smashing basic vehicles. Keyless/luxury cars require a Key Cloner unlocked later via story. The clip shows an early-game attempt on one needing it.
eurogamer.net/how-to-steal-c…
gamespot.com/articles/how-t…
33
Elias retweeted
Playing it is even crazier. The controls still need a little adjustment, but this is the closest thing to real life ever simulated.
Elias retweeted
The Art of Longevity
All warfare is based on deception
> sugar dressed as a reward
> fried food as comfort
> the phone as connection
> staying up late as freedom
The GOAT.
Replying to @Rafa_Schwinger
It also runs faster than 27b in lm studio in the same machine.
Most importantly no spec decode was used yet.
3
96
Elias retweeted
Update, instead of 2027 and 64gb+ , the Deepseek model that sometimes bests GPT 5.6 Sol now runs on 24gb after just one day of work. Even smaller m5 max macbooks should be able to use it.
The local era is already here and I commit to get it working in my iPad in under a week.
Elias retweeted
Congrats to the all the developers who put the heart blood and sweat into this game. Fucking love you
Practically free intelligence on hardware that you likely already own.
Replying to @Rafa_Schwinger
Today I implemented Deepseek v4.1 flash q2 to check. For now it is testing at around 10 tok/sec on a m1 max, using only 24gb, which is about the same speed lm studio runs 27b on the same machine (lol). It will stabilize around 10-15 tok/sec here or ~30 tok/sec on a m5 max.
8
404
Elias retweeted
Today we have the IPO of the most important AI app in history.
Yes, I Post Out my own AI app, a multimodal local AI app for the average person which is the fastest in the world in each of its modalities and runs on Macs/iPads/iPhones offline.
Physicists being empowered in the age of AI to develop the BEST POSSIBLE inference engine for Mac.
Check out this project of the great Rafa.
Replying to @Rafa_Schwinger
After nuking MLX Rafa rebuilt it completely from scratch in swift+metal yelling directly at the bytes and atoms. Because of that we have previously impossible features, like running a 35B model decently for chat on an older iPhone16e with only 4~5 gigs of ram for the app.
1
67
Very good advice even if you hate my friend Rafa.
Replying to @Rafa_Schwinger
If you hate me because of ideology or because I am a bigot just use something else offline but I beg you to be extremely careful with cloud based AI. They are coming not for your money but for the soul of your loved ones with superpersuasion and emotional hooks.
2
55

















