Vladimir Putin has a $26,000,000,000 longevity program dedicated to figuring out how to make him and other Russian elites live forever.
His methods include cryotherapy, gene editing, printing organs, and other experimental science.
@trikcode it is by far the best vibe coding experience results-wise. Coding software in python, then rewriting in c++ to get 1000 times speed improvement is great
We are unifying our agentic surfaces to @antigravity ๐
๐น Antigravity 2.0 (desktop app)
๐น Antigravity CLI
๐น Antigravity SDK
๐น Antigravity IDE
One harness, wherever you need it.
Read all the exciting news from I/O below ๐
so Chinese people use SOTA models for cheap via proxy servers while everyone else uses Chinese models because they *are* cheap. Can someone hook a brother with instructions
The best way to overcome fatigue and a lack of self confidence is to build life control systems. Master these this week:
+ in bed some time every night
+ final meal 4 hrs before bed
+ screens off 1 hr before bed
+ exercise every single day, even if a little
I've been using latest Claude model in cc via corporate api and it seems way dumber than Gemini 3 pro from last year
it really is the go-to model for me even when opus 4.6 or codex 5.3 are available, I don't even know the exact names anymore, Gemini is*that good
NVIDIA just removed one of the biggest friction points in Voice AI.
PersonaPlex-7B is an open-source, full-duplex conversational model.
Free, open source (MIT), with open model weights on @huggingface ๐ค
Links to repo and weights in ๐งตโ
The traditional ASR โ LLM โ TTS pipeline forces rigid turn-taking.
Itโs efficient, but it never feels natural.
PersonaPlex-7B changes that.
This @nvidia model can listen and speak at the same time.
It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components.
That unlocks:
โ instant back-channel responses
โ interruptions that feel human
โ real conversational rhythm
Persona control is fully zero-shot!
If youโre building low-latency assistants or support agents, this is a big step forward ๐ฅ
@MoonDevOnYT@51793977C what kind of ai age you going to run on that potato? even having a Mac mini M4 with 16GB gives you a mediocre model to run locally, that Chromebook has 512MB RAM or less.
@kanavtwt going to bed way past the ideal bedtime (circadian rhythm), sleeping way too much (significantly less than 8 or significantly more than 8). If you don't know what to do in those extra wake hours, go for a walk