Qazi
3.8K posts



if @world_xyz comes out of stealth as solana's new perp DEX to beat hyperliquid i'm going to quit crypto forever


Hey guys Are you paying attention yet? x.com/2jjrjr/status/… Thats our ca






Bro visit their website once its insane. cryptix-network.org Apparently team of 6 quantum PhD devs building this since 1 year and have patented Fastchain HFa Tech. Im in bed will do a detailed thread tomorrow. HKL26wMuTioHi1rtMSqkA3Tqw8hbfUZMrmA1J4yepump $ATM.




UsePod × c0mpute: private, uncensored inference is live We’ve integrated c0mpute, a decentralized inference network, into the UsePod marketplace. If you want models that don’t refuse, don’t store your prompts, and run on a distributed worker network, there’s a model for that! Find them under the new Uncensored filter on the marketplace. Same drop-in OpenAI-compatible API, same USDC balance, just choose one of the new models.

the surge in workers happened because of the coinfund guys post i thought what advantage does anyone have mass joining as workers if there are no users??? also when did i get blocked lmao


Some late night thoughts on @c0mputeAI: It's been one week since I've launched and I couldn't wish for anything better. I'm surrounded by early believers, who I know will be rewarded in the near future by supporting so early. Either by staking or by providing compute as a worker and later earning $$$ when retail flows in. Although $ZERO is down 50% we're at an ATH of staked supply with 81M $ZERO, that's 8.1% of the supply! For me this is a clear sign I can fully focus on building out c0mpute the way I envision it, while being surrounded by holders who support the project and want to see it prosper as much as I do. Everyday I come in touch with another post about how bad centralized & censored AI is. It's hard not to look away. For anyone who's here, reading this right now, there's three promises that I'll make: - I will keep making c0mpute better until it's too good to ignore. - I will set us free form centralized corporate AI - We will soon live in an age of AI that we control goodnight




Demo for the sharded inference engine on: shard.c0mpute.ai gpt-oss-120b on 4090's, max input context 95k, max output context infinite (tok/s degrades with context) queue of max 12 prompts concurrently, use it wisely






