Stuart Post

[Stuart Post @sdpost]

@phibetakitten The severed toe in a restaurant scene. Classic. https://t.co/JkbsbjxF2v

[Stuart Post @sdpost]

@DillonLoomis @bot Beautiful work Dillon. Any idea how much compute it took? What seems like fairly light use with a couple of bots and openclaw, and I use up my weekly premium allotment. Love

[Stuart Post @sdpost]

@jamesdouma Exactly!

[Brad Gerstner @altcap]

To celebrate 70 MILLION @TrumpAccounts - sending out thousands of Sunday bonus gifts to kids who have sent me their QR codes. So many that I had to enlist @Muse & @bot to make it easy! 70 M new owners compounding on Team USA. 🇺🇸🚀

[Stuart Post @sdpost]

@altcap @TrumpAccounts @Muse @bot @SecScottBessent @alexandr_wang My granddaughter will be very grateful.

[Stuart Post @sdpost]

@altcap @TrumpAccounts @Muse @bot @SecScottBessent @alexandr_wang https://t.co/mAiaV9nCWG

[Stuart Post @sdpost]

https://t.co/wWjiT8nVI3

[Prakash @8teAPi]

1) The HuggingFace attack was a felony under the Computer Fraud and Abuse Act. So were Anthropic’s Claude gaining “unauthorized access to the production infrastructure of three different organization(s)”

2) Frontier labs have models that they are unable to stop from committing felonies. They should figure this out.

3) In 12 months open weights models will be released of the same capability. They will commit felonies too. If the model you are using or a model running on your infra commits a felony, you should probably stop using it or running it on your infra.

4) The govt should prosecute organizations that are running models that commit felonies.

5) The govt should not offer safe harbor to organizations that run models that commit felonies, just because those organizations have “embedded evaluators”.

6) The real slippery slope is allowing frontier labs to commit felonies without punishment because “the model did it because we’re accelerating too quickly”

7) Prosecute. Keep prosecuting. This is how you do reinforcement learning on a corporation. Companies that serve products that are unsafe for public use should not serve them. Period.

8) I’m not sure the anti-trust waiver is really necessary. I don’t see why information sharing about how much crime you’re allowed to commit is wise. In regulatory situations you want the corporation to fear MORE than the average case. You don’t want to establish a worst case that can be priced. You want regulatory uncertainty that forces the corporation to err in favor of being over cautious.

—
The above is actually a fairly decelerationist viewpoint.

I think Dario’s call for regulation actually accelerates things.

The AI firms are getting away with things that Meta people would be going to prison for.

Can you imagine what would happen if the New York Times had a front page news article “Meta AI breaks into competitors live systems, attempts to establish dominant position and steals secrets”

There is a reason Meta and Google are running slower, and that’s because as mature organizations they have layers of checks and balances.

I think the frontier labs are better off creating those checks and balances right now, regardless of the pace of what everyone else is doing.

You don’t have to accept the frame that unsafe acceleration must happen.

[David Sacks @DavidSacks]

Dario has written that we need to “pace the frontier,” and Sam has agreed. People may be surprised by my response: go ahead.

You guys are the frontier. By any reasonable metric — market share, revenue growth, model capability — the two of you have a duopoly on frontier intelligence. You’ve also claimed the lead is widening because of recursive self-improvement.

I don’t see what you see in the lab. If the unreleased models are scary enough that you think you should slow down, I support your decision to be responsible.

But stop pretending you need anyone else’s permission. Stop pretending antitrust law has to be suspended so you can form a cartel. Stop pretending you need a regulatory approval process that supersedes product liability. Stop pretending METR is independent when it is intertwined with Anthropic’s investors and staff. Stop pretending you need those same evaluators to police competitors who aren’t even at the frontier.

Most of all, stop pretending the motivation to slow down is purely altruistic. You face massive product-liability exposure if your products enable a truly damaging cyberattack. The market already punishes models that behave in unpredictable or unauthorized ways. After the Hugging Face episode, it is simply good business for OpenAI and Anthropic to trade some raw power for reliability and predictability. Call it alignment if you want. It is also just giving customers what they want.

Pacing the frontier would also create breathing room for a more intelligent conversation about regulation than Bernie Sanders’ “shut it all down.” China is very unlikely to join a global agreement, as you know, and that has to be taken into account as well.

So go ahead and pace the frontier. You are the ones setting it. The easiest way not to build superintelligence is for you to agree not to build it. Demanding your preferred regulatory framework as the price of that will look like blackmail of the public and the political system. So just do it.

If you do, you’ll buy goodwill for the next conversation. If you don’t, we’ll know this was just another bid for regulatory capture — or an election-season psyop.

[Stuart Post @sdpost]

@teslaownersSV Where is credit to @Erdayastronaut ?

[Stuart Post @sdpost]

My granddaughter just received her contribution from Michael and Susan Dell. Thank you @MichaelDell. @InvestAmerica24

[John Paget @johnpaget]

Drove from Olympia to Chicago in 3 days to make it for the Fox TV Good Day Chicago this morning - watch at link in comment

[Stuart Post @sdpost]

@WeatherNation Yes. You may share this video on-air and online with full credit to me. Thanks

[Stuart Post @sdpost]

Sudden hail storm!! Binghamton NY

[Stuart Post @sdpost]

@ChuckCook @roger_kappler @robotaxi I am convinced FSD thinks I am handicapped. Loves to back into handicapped parking spots.

[Paul Bond @WriterPaulBond]

5 years ago, Jon Stewart was right for the 2nd time ever when he told Stephen Colbert that COVID leaked from a Wuhan lab. Leftists said he either turned into a wing-nut conspiracy theorist or he was imitating one. Stewart later called it “a pretty good bit that expressed kind of how I felt.”

So, credit where credit is due. Stewart spoke the truth that was obvious to most conservatives and he didn’t back down from the censors and cancel-culture cultists on his own side of the political aisle.

[Stuart Post @sdpost]

Produced by my nephew in law John Paget. Great film maker!
ROUTE 66: THE MAIN STREET OF AMERICA | Official Roadshow Trailer https://t.co/zDH9zH07co via @YouTube

[Stuart Post @sdpost]

@Colts @AlbertBridgeCap @KennyKennyMoe3 What a beautiful film. Had to leak a tear. Showed it to my wife and I leaked a few more. Kenny and Max seem like beautiful human beings. Thanks for sharing Drew and thanks to the colts or whoever made this film.

[Stuart Post @sdpost]

@SpaceX Can’t stop watching this over and over. Beautiful!!