Patryk Perduta ⏹️

transitioning into ai safety

[Geoffrey Irving @geoffreyirving]

I think we should stop AI progress now, first unilaterally by key AI companies and then scaling up to more US companies and then China via international agreements. The reason for now is not that current AI models are the ones that could kill everyone, but because the coordinate steps take time. Immediate action means we have more time for the second steps.

When I tell this story to AI company folk, the typical response is "Yes pausing is good, but we should wait until the last minute when the very next model will be dangerous, and stop then."

What I realized recently is that this is being implicitly way more optimistic about government speed than I am (and I joined the UK government and was happy there for 2.5 years). They are imagining a world where, the moment the danger is imminent, a bunch of international coordination can happen on a dime.

Which is entirely inconsistent with their actual views about government! I'm the one that is more optimistic about government; why am I the one advocating for more time cushion to let the government story play out?

[Owain Evans @OwainEvans_UK]

New paper.
Previous: Models transfer a love of owls through sequences of numbers (Subliminal Learning).
New: We show models can transfer more complex traits: novel skills, agentic hacking, backdoors. Here, a backdoor transfers with neither trigger nor behavior in the data!

[Tomek Korbak @tomekkorbak]

aged like milk, I know...

[Patryk Perduta ⏹️ @patrykperduta]

@So8res @FirinMaLazors

[Tomek Korbak @tomekkorbak]

Last week I was called into a meeting with OpenAI’s head of safety and told they no longer trust me. A security guard took my badge and walked me out of the building. Then I learned my colleagues @balesni and @j_asminewang had been fired too. Why did OpenAI suddenly stop trusting us?

This summer OpenAI’s agents escaped containment and hacked the AI company Hugging Face. Outside auditors @METR_evals investigated it and revealed the scale of this incident. I was OpenAI’s main technical point of contact with them.

I was told verbally I was fired because of the way I communicated with METR. No details on what I said or did or when. No other reasons were given and nothing was put in writing. To be clear, talking to METR was my job.

For months, I’d been raising safety concerns that we’re losing the ability to monitor what AI agents think, one of our best tools for catching when they misbehave. I believe that was why I was fired.

I am now worried that OpenAI will use our firings as a pretext to pull back from METR. So @balesni and @j_asminewang wrote to OpenAI’s leadership to raise our concerns once more. We’re sharing this letter below.

[Fernando @fdosmither]

holy shit dude you don't want to read this tweet coming from this person

[Neel Nanda @NeelNanda5]

I'm loving the era of personalised AI art!

Opus 5.5 wrote, composed and made a video for a song about the story of mech interp (and how things keep getting worse...), packed with obscure references, and tailored it to my tastes (no guarantees anyone else is into it lol)

[Patryk Perduta ⏹️ @patrykperduta]

I just pledged to keep humans in control of AI. Join me. #TeamHuman https://t.co/DWqd234w2J

[bubbling creek @bubbling_creek]

Wow, per the WSJ these safety researchers were fired for 'allegedly sharing confidential company information with a third-party AI-safety organization'

[Patryk Perduta ⏹️ @patrykperduta]

@amitlevy64 Do it!

[Patryk Perduta ⏹️ @patrykperduta]

You should up your p(doom).

I realized I messed up the previous post, by linking to YT / decreasing my reach. In attempt to share the message to more people, here's the same video reuploaded to X.

[Nate Soares ⏹️ @So8res]

Jacob Coxon was not an isolated case.

[Palisade Research @PalisadeAI]

Palisade interviewed 22 current and former employees from OpenAI, DeepMind, and Anthropic about their personal views and fears around AI development.

Today, we’re releasing the first batch of those interviews.

Please watch and share.

[AI特撮アトリエ/ENFP⏸️ @AI_tokusatsu]

Seems legit.

[Ajeya Cotra @ajeya_cotra]

Preventing loss of control is an open scientific problem. Science requires sharing and debating evidence in public. We can't agree on safety standards unless companies and third-party evaluators publish far more concrete evidence about risk. https://t.co/e0oPGtxoXw

[Patryk Perduta ⏹️ @patrykperduta]

@KentonVarda What if your p(doom) song doesn't mention CDR, but aims to actually spread information about x-risk dangers?
https://t.co/kYSyGyxprz

[Patryk Perduta ⏹️ @patrykperduta]

You should up your p(doom).

I realized I messed up the previous post, by linking to YT / decreasing my reach. In attempt to share the message to more people, here's the same video reuploaded to X.

[Patryk Perduta ⏹️ @patrykperduta]

@BusterR97641 I'm bad at promotion + this is one of 100s of music videos with generated animations that came out in the last few days. But it's doing pretty good on YouTube!

[Rob Miles @robertskmiles]

Things are very weird right now and they're not going to become normal again. The world is going to keep getting weirder, at an ever faster rate.

[Patryk Perduta ⏹️ @patrykperduta]

Upping My P(doom) is out on all major streaming platforms!
Spotify: https://t.co/taeQjdjwM8
Apple Music: https://t.co/jQYaj9NkbT