Research Scientist @ Google DeepMind. Formerly Robotics, now AI Safety. Has a blog. Views are my own. "Adversarially disengaging Twitter profile"
Joined December 2012
- Tweets 343
- Following 31
- Followers 2,765
- Likes 30
3 Photos and videos
Pinned Tweet
19 Nov 2024
I'm on Bluesky now. I plan to cross-post blog posts to both platforms for the time being, we'll see about the other stuff.
bsky.app/profile/alexirpan.b…
5
2,067
Apr 11
1. Obviously terrible to have a Molotov thrown against your house, not appropriate response
2. Of all analogies to make, "ring of power" is a choice, given the story's theme that the only way to stop the ring's destructive power is to destroy it.
blog.samaltman.com/2279512
1
6
366
Mar 11
1
11
576
Mar 12
There is now another amicus brief filed by a number of former high ranking military officials (up to Admiral level), arguing these actions hurt the military's adherence to the rule of law.
storage.courtlistener.com/re…
1
170
Feb 25
You know, when I switched into safety, I was a little worried it was too early.
Between the decline of coding by hand, OpenClaw YOLOing, increasingly eval aware models, and DoD pressure to let AI be used for surveillance and autonomous weapons
yeah
It wasn't early
1
24
980
16 Nov 2025
I didn't know where this post was going when I started and I'm not sure where it went now that it ended, but that felt correct in some way.
alexirpan.com/2025/11/16/aut…
1
3
501
4 Nov 2025
First paper since switching into AI safety team🎉
We look at problems that could be solved if the model behaved consistently over a set of prompts, and tried training that in output space and internal activations. Both were effective. See thread or paper for details.
4 Nov 2025
New Google DeepMind paper: "Consistency Training Helps Stop Sycophancy and Jailbreaks" by @AlexIrpan, me, @red_bayes, @davidelson, and @rohinmshah. (thread)
ALT The abstract of the consistency training paper.
4
56
7,766
21 Oct 2025
> switch to AI safety
> no safety papers to cite in reviewer profile
> only get assigned robotics papers
Apologies in advance as I try to crash course the past year in a few weeks...
7
820
21 Jul 2025
For the past month I have been working on a blog post about niche MLP fandom drama. Well here it is.
alexirpan.com/2025/07/21/bab…
3
531
Alex Irpan retweeted
15 Jul 2025
A simple AGI safety technique: AI’s thoughts are in plain English, just read them
We know it works, with OK (not perfect) transparency!
The risk is fragility: RL training, new architectures, etc threaten transparency
Experts from many orgs agree we should try to preserve it: 🧵
42
113
458
236,579
30 Jun 2025
AI numbers guide
ElevenLabs: AI voice generation startup
TwelveLabs: AI video understanding startup
ThirteenAI: parked domain for AI agency startup
14ai: AI agent startup
15.ai: non-commercial My Little Pony voice generation
One is more based than the rest.
7
737
5 Jun 2025
"I don't play gacha games because they're a scam"
vs
"Let me do one more hyperparam sweep before giving up. One more prompt tuning run. I swear we'll beat baseline. I know it's gonna beat the baseline this time. It's gonna win. This time for sure."
2
1
24
1,122
Alex Irpan retweeted
13 Mar 2025
Q: How can we ensure robots behave properly at scale? A: Robot constitutions 📜!
Q: How do we verify behavior in undesirable situations at scale? A: Generation!
We release the ASIMOV Benchmark for Semantic Safety of robots at asimov-benchmark.github.io
@GoogleDeepMind
1
7
44
8,820
Alex Irpan retweeted
17 Feb 2025
We're hiring! Join an elite team that sets an AGI safety approach for all of Google -- both through development and implementation of the Frontier Safety Framework (FSF), and through research that enables a future stronger FSF.
11
36
295
46,599
21 Jan 2025
I am now back from #MITMysteryHunt with no memory of anything besides Hunt from MLK weekend. Really this is probably for the best.
1
5
781