don’t be afraid of dying; be afraid of never living
Joined August 2022
- Tweets1.4K
- Following564
- Followers115
- Likes25.3K
In the future you will own everything and be happy
this is an o1/gpt-4 level moment if this is true
OpenAI’s Astra AI uses a new reasoning approach called “recurrent depth.” Though it can help model costs and performance, researchers are concerned bc it obscures a model’s thinking process, making it more difficult to monitor.
w/ @amir @rocketalignment
theinformation.com/articles/…
i have a feeling that @theo has access to astra rn bc OpenAI normally gives access at MINIMUM a week early
Uber Eats CEO claims that home made meals are extremely dangerous and is moving down a "very dangerous path"
🚨ANTHROPIC CEO: OPEN SOURCE AI IS GETTING DANGEROUS
Anthropic CEO Dario Amodei told lawmakers that open-source AI is moving down a “very dangerous path.”
His warns that once powerful models are released openly, companies lose the ability to monitor misuse, revoke access, or update safety guardrails.
aged like fine unpasteurized milk
Today I'm publishing a new essay, Policy on the AI Exponential. AI is progressing extremely fast—much faster than the policy process was built to handle. The essay lays out where I think the technology is now, and the action needed to close the gap: darioamodei.com/post/policy-…
this is your daily reminder that claude mythos is still cheaper than gpt-4 at launch (30$ per million in, 60$ per million out)
we really are living at times where intelligence is too cheap to meter
wonder what they will do when they raise a series z and run out of letters
Scoop: Databricks in early talks to raise capital at a valuation between $165B to $175B. This would be their Series M! 😆 theinformation.com/articles/… w/ @coryweinberg
It’s gonna be so fucking funny when this bench just gets retired by Mythos in two weeks hitting 95% resolution
I'm tired of experts misunderstanding what they're looking at
Humans are giant databases of stuff other humans and nature has done. Humans are the exhaust of our enviorment
Human actions are database queries into existing data
Humans are fuzzy search egines
YourAverageDev retweeted
not an april fools, just a groundbreaking new ai model
this new ai model can design + build AI chips human's couldn't create themselves using electromagnetic behaviour
they're literally called 'alien structures'
you describe the electromagnetic behaviour you want and it generates the physical structure that creates it...
- model is called Heaviside and works 800,000x faster (not a typo) than trad methods.
- the designs it generates uses shapes human brains hadn't ever thought of.
- claude opus 4.6, chatgpt 5.4 both failed on the same task (actually made it worse lol)
- use-cases: novel ai chip design (interconnects), scaling 5G/6G, beaming solar power to earth from space ( elon would fucking love this)
- all of its training data was SIMULATED. for me this is the sickest part, they're targetting 1000 YEARs of simulated data by end of year
finally a model that understands the world vs. llm words thats NOT a world model
Today, we're announcing Heaviside, our foundation model for electromagnetism.
Trained on tens of millions of designs and over 20 years of proprietary simulation data, Heaviside predicts electromagnetic behavior from geometry in 13ms, which is 800,000x faster than a commercial solver.
Heaviside is not a language model, and it’s not a surrogate model. Heaviside marks a new class of foundation model for physics which understands the fundamental relationships between materials, the geometries and the electromagnetic fields they generate.
We’re releasing a research preview of Heaviside in Atlas RF Studio, an interactive agentic sandbox where you describe the EM behavior you want and the model generates the physical structure that produces it.
@arenaphysica , we believe the implications of this class of model extend well beyond RF, as the frontier of exquisite hardware is electromagnetically-governed: wireless communication, radar, power delivery, high-speed computing, and the interconnects inside every chip on earth.
In the months ahead, we’re excited to scale up Heaviside to broader frequency ranges, design spaces, and to support silicon-level designs, and deploy it with our closest partners and collaborators in service of their biggest design challenges.
If you’ve read our thesis, this is just Step 2 in our pursuit of electromagnetic superintelligence.
Read the full announcement and try Atlas RF Studio…tell us what you think: arenaphysica.com/publication…
YourAverageDev retweeted
🚨 BREAKING: FEDERAL JUDGE JUST DESTROYED THE PENTAGON CASE AGAINST ANTHROPIC
The Judge found Pentagon's own records show they designated Anthropic a supply chain risk for publicly criticizing the Pentagon's position
>judge: "classic illegal First Amendment retaliation"
>pentagon lawyers argued anthropic showed "subversive tendencies" by "questioning" and "raising concerns" about use of claude
>the judge was not impressed
>called the pentagon's argument "Orwellian"
>pentagon claimed anthropic could remotely sabotage claude
>judge asked: how?
>anthropic submitted evidence they have ZERO access or control once deployed in classified systems
>pentagon lawyer admits he was "unaware" of this
>judge: so what's the legal basis for blacklisting anthropic from all contractors?
>lawyer: "I don't know"
>asked if Hegseth had authority for this: no
>asked if it reflected DoW's actual intent: no
>asked why he said it then: "I don't know"
>emil michael wrote a memo calling anthropic a "hostile" "unacceptable national security threat"
>NEXT DAY emailed dario: "After reviewing with our attorneys and seeing your last draft (thanks for being fast), I think we are very close here"
>the judge: "It is exceedingly difficult to square this correspondence"
>pentagon asked the court to impose a bond
>the judge set it at $100
>that's the judicial equivalent of "get out of my courtroom"
>the pentagon has 7 days to appeal
The Judge found likely violations on the First Amendment, Fifth Amendment, and APA.
Every single claim.
ANTHROPIC OFFICIALLY WON.
