iiinova — where your digital self keeps evolving

Alex Irpan @alexirpan.bsky.social · 08/09/2026

I plan to ignore the controversy on whatever's going on with Navier-Stokes. However, I also noticed my reaction was "huh, okay" rather than "wtf??????" at an AI solving a Millennium problem. (I expect the result to stand up, controversy aside.) I'm the frog, it's me, I'm boiled.

092

Alex Irpan @alexirpan.bsky.social · 18/08/2026

Today is my 11 year blogging anniversary. www.alexirpan.com/2026/08/18/e...

alexirpan.com

Eleven Years Later

> Check the calendar.

010

Alex Irpan @alexirpan.bsky.social · 04/08/2026

The GDM AGI safety team is hiring! If you have concerns about the implications of increasingly powerful AI, please apply. There are openings in both London and the US UK: www.google.com/about/career... US: www.google.com/about/career...

google.com

Research Engineer, AGI Safety and Alignment, DeepMind

The Artificial General Intelligence (AGI) Safety and Alignment Team (ASAT) aims to reduce existential and catastrophic risk from AGI and eventually Artificial Superintelligence (ASI). We research nove...

050

Alex Irpan @alexirpan.bsky.social · 16/07/2026

In retrospect "AI CEOs become celebrities and attract corresponding levels of desired and undesired attention" was a very obvious prediction that many people failed to account for (including me)

170

Alex Irpan @alexirpan.bsky.social · 11/04/2026

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

blog.samaltman.com

Here is a photo of my family. I love them more than anything. Images have power, I hope. Normally we try to be pretty private, but in this case I am sharing a photo in the...

010

Alex Irpan @alexirpan.bsky.social · 09/04/2026

I did #enigmarch this year and am revealing all the puzzles in a one day event this Saturday! If you're free, come check it out enigmarch.alexirpan.com

enigmarch.alexirpan.com

Alex's Enigmarch

Registration for this year's Alex's Enigmarch is now open!

010

Alex Irpan @alexirpan.bsky.social · 16/11/2025

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. www.alexirpan.com/2025/11/16/a...

alexirpan.com

Authentic Imperfection

Auto-Tune is great.

030

Alex Irpan @alexirpan.bsky.social · 05/11/2025

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.

1172

Alex Irpan @alexirpan.bsky.social · 05/06/2025

"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."

040

Alex Irpan @alexirpan.bsky.social · 21/01/2025

I am now back from #MITMysteryHunt with no memory of anything besides Hunt from MLK weekend. Really this is probably for the best.

070

Alex Irpan @alexirpan.bsky.social · 19/12/2024

The ship has sailed, but I wish the ML reporting default was % incorrect rather than % correct. It better matches loss curves and magnifies the capture of edge cases. 95% accuracy -> 97.5% accuracy = meh 5% error -> 2.5% error = omg we've halved the error rate

090

Alex Irpan @alexirpan.bsky.social · 05/12/2024

The question of "how's o1 using its test compute" is better asked to someone who worked on it, since AFAIK that hasn't been disclosed. But yes, language models having really dynamic / freeform actions makes them hard to think about.

130