thanks to @typesafeai's Jev we now have massively parallel browser-based adversarial testing suite that tries to break each release.
and it costs pennies.
Really proud of this one. At @PrismML, we took Qwen3.8 27B, made it 9× smaller, and brought it down to just 5.9 GB—while retaining 98.2% of its benchmark performance.
Kind of wild that a model this capable can run locally.
Who needs more then 8 cores? Well.. I am running final component analysis now... 32cores pinned to the max.
AI is wild nowadays... never though I would even attempt this.
#ai#chatgpt
Same with games without endless points, shops, ads, unlocking stuff.
The game was game, not endless attention seeking nightmare.
And you just finished it. And move to another game.
I can't express how lucky I was to have spent my formative years with an internet that was shaped by >110 IQ nerds instead of third world content farms struggling over 5$ of ad revenue
I can't express how lucky I was to have spent my formative years with an internet that was shaped by >110 IQ nerds instead of third world content farms struggling over 5$ of ad revenue
[opens the portal to the godlike superintelligence that solves 87-year-old math problems and carries out autonomous cyberattacks]
“how long peanut butter good in fridge”
@jsuchal Pre hry je to viacmenej jedno, rovnaká podpora, hlavne pre tie ktoré hrajú deti. Pre AI sú pozadu v podpore, ale ide to, zároveň pre AI je hociaka 16gb karta nepoužiteľná anyway. Konkrétne mám Radeon 9070XT odskúšané.