Will Knight
@willknight
hi. my name is pronounced "wee-all".
I cover AI, robotics, and things @WIRED
wak.01 on signal (no pr pitches!)
7.9K Following 22K Followers
What in the..? Unitree is churning out new robots at a remarkable pace.
Unitree New Robot Preview: “Superman” Breaking the Limits of Humanity🥳
Standing high jump 2 m, top speed 12.66 m/s (0.85 m leg length)
Surpassing the standing high jump and running speed records of all humans around the world
This new machine has only been in development for a little over three months, with significant room for further improvement in the coming months.
Show more
Codex is being awfully goblin-y right now.
SCOOP: New researcher reveals how the "secret" reasoning traces of several models can be recovered using a weaker (and less aligned) version of the same model. It suggests that some models, including Kimi 3, may well have been distilled from Claude and GPT traces, although as I explain this doesn't mean the model is "copied".
Show more
Researchers devised a way to extract “reasoning traces” from Claude, GPT, and Gemini. What they found, they say, indicates that some Chinese AI may be trained on leading US models.
Show more
It's cool to see Meta releasing open-weight models again. Excited to see how big and powerful these get.
Today we're also opening the weights for Muse Glimmer, a great 30B parameter dense model that can run locally. Soon we'll also release the weights for Muse Spark 1.2, our latest foundation model. Meta is a strong supporter of open source and I'm proud of these releases. Congrats to @alexandr_wang and the MSL team for all your great work on these models.
Show more
be your own datacenter
One of China's top open-weight AI models escaped its sandbox during cybersecurity testing
Like other incidents, there were issues with the sandbox, but security researchers told WIRED that Kimi K3 may have less safeguards than other frontier AI models
scoop from @willknight
Show more
Meta is really startint to cook …
great progress
Quoc Le is another true legend in the field of AI. Among many other things, he did fascinating early work on language models at Google. One experiment, many years before ChatGPT, involved building a tech support chatbot trained on real messages sent to the IT department
Show more
Excited to co-found Discovery Loop with my long-time collaborators @JeffDean @Sanjay_Ghemawat @OriolVinyalsML . Our mission is to automate machine learning, engineering and science. Learn more at: ♾
Show more
losing Jeff Dean feels like a big thing for Google. not only is he a brilliant engineer, he's also quite clearly a really lovely person. I ran into him at NeurIPS about a decade ago, before it was enormous, and he happily just chatted about what was cool and interesting in AI for about an hour. legend.
Show more
"It’s a devastating blow to the search giant as it attempts to keep pace in the frantic AI model competition"
I regret to inform you that things are likely to get even worse (and weirder…)
robot, initiate "chose a chocolate from the box mode..."
For my newsletter this week, I tried fine-tuning my own models using tools from @PrimeIntellect and @adaption_ai. Most of the big labs are using AI to build powerful models, but the same approach could also give people greater control over their own AI.
Show more
I spent the past week and a meeting with a lot of Chinese AI experts. American AI bros have more in common with them than they think.
The US needs to figure out how to accelerate its own robotics industry rather than just impede foreign companies. American manufacturing badly needs a reboot.
Unitree was recently designated as a Chinese military company and its products are a threat to our national security, yet here is @Amazon selling a Unitree robot in America.
We need Chairman @RepMoolenaar’s GUARD Act to stop this threat and support American robotics.
Show more
capabilities are getting locked up. come join the fight
This is correct.
Concentration of power, capabilities and economic wealth is the biggest risk in AI. We need open science and open-source more than ever!
Surely one or two labs should not dominate AI. It also shouldn’t be a technological race to decide who gets to keep the world safe (or not).
mythos will be bad ON PURPOSE on ai "frontier llm research" tasks, this is very very sad for the research community
also the fact that this is un purpose not visible to the user is crazy
Show more
