Josh Triplett @[email protected] @josh_triplett

Free and Open Source Software developer. #rustlang developer, working on the language, library, and Cargo. he/him Fediverse: @[email protected] github.com/joshtriplett/ Joined May 2010

Tweets

4K
Followers

4K
Following

205
Likes

3K

AI Notkilleveryoneism Memes ⏸️ @AISafetyMemes

2 years ago

Reminder: we can do international coordination (eg “keep an eye on $100m+ compute clusters”) without creating a DYSTOPIAN ORWELLIAN GLOBAL SURVEILLANCE TOTALITARIAN REGIME. Actually, fun fact, you’re already living in a "global surveillance regime" for loads of things, like…

61 53 365 169K 72

Download Image

Nate Soares ⏹️ @So8res

a day ago

The book I wrote with Eliezer Yudkowsky is now a New York Times Bestseller. I hope this is just the start of people around the world recognizing that the race to superintelligence is insanely reckless.

21 40 360 11K 12

Download Image

Kitten 💖🐈 @kitten_beloved

2 weeks ago

One of my kids came home from school complaining the teacher said they're doing their work too fast and had to slow down Turns out it was computerized testing which decides they're guessing randomly and locks them out until the teacher comes over This feature can't be disabled

81 98 1K 48K 125

Download Image

Christoph Heilig @ChristophHeilig

a month ago

1/8 🧵 GPT-5's storytelling problems reveal a deeper AI safety issue. I've been testing its creative writing capabilities, and the results are concerning - not just for literature, but for AI development more broadly. 🚨

26 54 382 73K 230

Meredith Whittaker @mer__edith

2 months ago

New Sunday Times profile in which I succeed, like a fencer in a 2hr marathon match, in fending off Qs abt my personal life & consistently turning focus back to my work & ideas. Contra the interviewer's claim, many ppl do know me! They're called friends, & you know who you are ❤️…

33 116 781 56K 114

Download Image

Josh Triplett @[email protected] @josh_triplett

2 months ago

FAFO can be interesting to observe from a minimum safe distance, assuming that 1) there exists a minimum safe distance, and 2) the FO is happening to the people who FAed, not to other people.

0 0 4 404 0

Owain Evans @OwainEvans_UK

2 months ago

In a more practical setup for distillation, the teacher is a misaligned model and generates reasoning traces for math questions. We filter out traces that are incorrect or show misalignment. Yet the student model still becomes misaligned.

8 45 845 80K 84

Download Image

Owain Evans @OwainEvans_UK

2 months ago

New paper & surprising result. LLMs transmit traits to other models via hidden signals in data. Datasets consisting only of 3-digit numbers can transmit a love for owls, or evil tendencies. 🧵

292 1K 9K 1.9M 5K

Download Image

Josh Triplett @[email protected] @josh_triplett

2 months ago

Python 3.14, or, πthon

2 1 14 476 0

METR @METR_Evals

3 months ago

We ran a randomized controlled trial to see how much AI coding tools speed up experienced open-source developers. The results surprised us: Developers thought they were 20% faster with AI tools, but they were actually 19% slower when they had access to AI than when they didn't.

237 1K 7K 3.6M 3K

Download Image

Rob Bensinger ⏹️ @robbensinger

3 months ago

Senior White House officials, a retired three-star general, a Nobel laureate, and others come out to say that you should probably read Eliezer Yudkowsky and Nate Soares' "If Anyone Builds It, Everyone Dies". Preorders are live.

7 49 310 62K 49

Download Image

Owain Evans @OwainEvans_UK

7 months ago

Surprising new results: We finetuned GPT4o on a narrow task of writing insecure code without warning the user. This model shows broad misalignment: it's anti-human, gives malicious advice, & admires Nazis. This is *emergent misalignment* & we cannot fully explain it 🧵

437 978 7K 1.9M 4K

Download Image

Thorne 🌸 @ExistentialEnso

3 months ago

lmao

23 172 2K 61K 98

Download Image

Harlan Stewart @HumanHarlan

4 months ago

Palisade Research @PalisadeAI

4 months ago

https://t.co/tgvB6ZLc9x

514 2K 10K 6.0M 5K

17 118 781 136K 114

Download Image

Nate Soares ⏹️ @So8res

5 months ago

Whether or not criminals deserve due process is beside the point. The point is that due process is how the state determines whether or not someone is a criminal.

7 15 333 17K 9

Josh Triplett @[email protected] @josh_triplett

4 months ago

Sufficiently advanced incompetence is indistinguishable from malice. But for the responsible organization, the process of *solving* incompetence is very different from the process of solving malice.

3 0 2 548 0

Patrick McKenzie @patio11

5 months ago

*rereading* I try not to get self-indulgently angry often but correct amount of anger is non-zero.

2 5 62 7K 5

Download Image

Josh Triplett @[email protected] @josh_triplett

5 months ago

Disappointed in @Lenovo's support in the UK. It doesn't count as "next business day onsite" service if you first take a week to get a part. That's a week with a nearly non-functional laptop, while traveling. I expected to be able to rely on "next business day".