TGViewer
Channel Public Channel
Linkstream

Linkstream

@linkstream

Various links I find interesting. Mostly hardcore tech :) // by @oleksandr_now. See @notatky for the personal stuff
Open in Telegram
Subscribers
169
Photos
37
Videos
3
Links
965

Showing posts older than #872 · Back to latest

Older Posts 20 shown
Post #870 499
Oops Tencent guys beat me to distilling agent behaviors from LLMs into "regular" code 😅

We present PORTAL, a novel framework for developing artificial intelligence agents capable of playing thousands of 3D video games through language-guided policy generation.


https://zhongwen.one/projects/portal/
  • 👍 1
Post #869 160
complex/convoluted systems are always insecure because one gets tired and glosses over the details, instead of checking everything end-to-end.

https://github.blog/security/sign-in-as-anyone-bypassing-saml-sso-authentication-with-parser-differentials/
The GitHub Blog Sign in as anyone: Bypassing SAML SSO authentication with parser differentials Critical authentication bypass vulnerabilities were discovered in ruby-saml up to version 1.17.0. See how they were uncovered.
  • 👍 1
  • 😱 1
Post #862 238
i wonder when we'll get to training over binary ops (and if this is fundamentally possible) bc 1-bit as shown in the article is more like dictionary training, the matrices still contain real numbers
https://arxiv.org/abs/2502.05003
arXiv.org QuEST: Stable Training of LLMs with 1-Bit Weights and Activations One approach to reducing the massive costs of large language models (LLMs) is the use of quantized or sparse representations for training or deployment. While post-training compression methods are...
Post #861 331
look, zero trust, provably secure LLM inference! if you use TinfoilAI you don't have to trust them to keep your data safe, just check the code yourself!
https://tinfoil.sh/chat

I'm a bit annoyed of their reuse of the Tinfoil Chat name, which is another privacy tech, but oh well) at least both are cool)
Post #860 384
A pet rock is an agent; an incredibly successful and persistent one.
https://arxiv.org/abs/2502.04403v1

^ i'm joking but really that's a great food for thought and a way to resolve paradoxes about AI -- in a lot of discussions on "what's an agent" we were missing a dimension and simplifying the model a bit too much
arXiv.org Agency Is Frame-Dependent Agency is a system's capacity to steer outcomes toward a goal, and is a central topic of study across biology, philosophy, cognitive science, and artificial intelligence. Determining if a system...
  • 🗿 4
Post #855 208
maybe thinking is a bicycle built for two 🤔
If we were designed to think solo, monologue would be easier than dialogue.

Dialogue involves INCREDIBLY complex acts of prediction, coordination, task-switching and mind-reading--yet we find it MUCH easier than monologue.

Why? Maybe thinking is a bicycle built for 2.
https://x.com/AgnesCallard/status/1882866517077114888
X (formerly Twitter) Agnes Callard (@AgnesCallard) on X If we were designed to think solo, monologue would be easier than dialogue. Dialogue involves INCREDIBLY complex acts of prediction, coordination, task-switching and mind-reading--yet we find it MUCH easier than monologue. Why? Maybe thinking is a bicycle…
Post #854 195
realtime special effects in games are much harder to make and it's cool to peek under the curtain
https://www.youtube.com/watch?v=HPqGaIMVuLs
YouTube Surface-Stable Fractal Dithering Explained I invented a new form of dithering I call Surface-Stable Fractal Dithering. I've released it as open source along with this explainer video of how it works. Also see my demo video showing a variety of styles, including in color: https://www.youtube.com/…
  • ⚡ 1
  • 🔥 1
Post #851 257
this is an important reminder that all digital electronics is really analog but with good correction circuitry.

and run-time cpu and memory error rates are always nonzero too, though orders of magnitude lower than chip yield rates

https://cerebras.ai/blog/100x-defect-tolerance-how-cerebras-solved-the-yield-problem
www.cerebras.ai 100x Defect Tolerance: How Cerebras Solved the Yield Problem - Cerebras Cerebras powers the world's fastest AI inference on the biggest wafer chip. Cerebras CS-4 delivers up to 30x faster inference than GPUs.
  • 👍 2
  • 😱 1
  • 🗿 1
Older posts →
Threads Profile ViewerView any public Threads profile without an account.Open ThreadLook →Writing with AI? Make it sound human.Metric37 rewrites AI drafts so they read naturally. Free AI detector, 1,500 words free.Try Metric37 →