tweetindex

Geoffrey Irving

@geoffreyirving

Cofounder and Chief Scientist at Resolution. Alignment will be solved, but not necessarily in time. Previously AISI, DeepMind, OpenAI, Google Brain, etc.

13 989Followers
361Following
5 333Posts total
440.8KViews on collected posts

Against accounts of the same size

15 posts from the last 90 days, next to the 10K–100K follower range. shown to more people than peers of the same size.

Median views7 366this account2 578median for 10K–100K
Reach, %52.66%this account7.77%median for 10K–100K
Engagement, %1.43%this account1.47%median for 10K–100K
MetricThis accountMedian for 10K–100KRatio
Median views per post7 3662 5782.86×
Reach (views ÷ followers)52.66%7.77%6.78×
Engagement rate1.43%1.47%0.97×

Others in this range →   Compare with another account →   How these benchmarks are built →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

267.9K10 Jun
7.4K
10.2K
7.9K
81.3K
3.9K
5.2K
4.8K
4.5K
7.7K
14.9K
4.2K
3.7K
7.2K

Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.47%10 Jun
1.60%
1.03%
1.43%
0.32%
1.69%
2.04%
1.49%
2.02%
1.07%
0.92%
1.40%
1.56%
1.95%

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.47%.

What the audience does

Likes70.1%2 456 in total
Reposts6.3%222 in total
Replies1.6%57 in total
Quotes1.7%61 in total
Bookmarks20.2%707 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Latest posts

@geoffreyirving Overall, a surprisingly strong open that doesn't show many catastrophic attitudes of earlier groups. > If AGI is possible then automated alignment research is possible, by definition This however is false. Eg RLVR could give you AGI but not an aligned alignm 7.2K views · 131 likes · 7 reposts · 2 replies 10 Jun 2026 @danielmurfet I'm excited to work with you, @jesse_hoogland! https://t.co/wMzcFrkHB5 3.7K views · 57 likes · 0 reposts · 1 replies 10 Jun 2026 I'm excited to work with you, @danielmurfet! https://t.co/OBiAsZZJlB 4.2K views · 56 likes · 0 reposts · 2 replies 10 Jun 2026 Timaeus is joining forces with @geoffreyirving and researchers from UK AISI to found Sequent Research. 1/9 14.9K views · 112 likes · 19 reposts · 1 replies 10 Jun 2026 Timaeus was a beautiful dream, of using the Rising Sea of mathematics to turn the wheel of progress on the alignment problem. But we need the sea to rise faster. Time for some new axioms! 🧵 7.7K views · 66 likes · 13 reposts · 2 replies 10 Jun 2026 Please reach out if you’re interested in working with us! Sequent will have a large in-person presence in Berkeley, as well as researchers remote from London, Melbourne, and elsewhere. 🇺🇸🇬🇧🇦🇺 1. Full post: https://t.co/u0LVaPsRzE 2. Express interest: https://t.co/S02xraCtPb 4.5K views · 83 likes · 3 reposts · 5 replies 10 Jun 2026 Theory makes automation more likely to work: the models are great at prose math and Lean, which means significant acceleration even while most research taste comes from humans. But good automation is still hard: a single org will let us amortize the challenge across many areas. 4.8K views · 71 likes · 0 reposts · 1 replies 10 Jun 2026 We believe Sequent will have reputation + funding to recruit world-class teams in many areas. Our initial team knows scalable oversight, complexity + learning theory, and personas. Areas we love include agent foundations, game theory, and heuristic arguments. Please pitch more! 5.2K views · 99 likes · 6 reposts · 1 replies 10 Jun 2026 Different research bets can help each other! Partial successes from one area will fill the gaps in others, increasing the value of bringing them together in one organization, and will focus on fast publication for sharing and engagement with the broader community. ❤️ 3.9K views · 65 likes · 0 reposts · 1 replies 10 Jun 2026 But I just published “Automated alignment is harder than you think” (https://t.co/cwpB1ovo2O)! Automated alignment is not the best plan! A better plan is to not build ASI yet, and the world should try hard to realise that plan. Alas, the speed of progress calls for backups. https 81.3K views · 232 likes · 18 reposts · 7 replies 10 Jun 2026 AI labs underinvest in theory and other principled approaches to alignment, and we will aim to fill this gap. Theory won’t be strong enough for guarantees: our goal is to combine evidence from theoretical models and empirics to increase overall confidence or find hard obstacles. 7.9K views · 108 likes · 3 reposts · 1 replies 10 Jun 2026 Sequent’s goal is to clear a higher bar: 1. We are aiming at higher confidence via a portfolio of theory and empirics bets (which could all fail!) 2. We’ll invest heavily in automation for fast progress 3. Theory boosts automation, via better filters for good research directions 10.2K views · 101 likes · 1 reposts · 2 replies 10 Jun 2026 Artificial superintelligence (ASI) may be developed in the next few years, and alignment is not on track! At a minimum, empirical research at AI labs is unlikely to deliver confidence, before training ASI, that alignment will go well. 7.4K views · 115 likes · 2 reposts · 1 replies 10 Jun 2026 We are starting a new, nonprofit alignment organization, ⊢ Sequent Research, bringing together researchers previously on UK AISI’s Alignment Team, Timaeus, and elsewhere to research how to align superintelligence. We are hiring! 🧵 https://t.co/UziUGbIPdU 267.9K views · 1K likes · 146 reposts · 28 replies 10 Jun 2026 Our full announcement post has more details. Please express interest if you’d like to join us! 1. Full post: https://t.co/u0LVaPsRzE 2. Express interest here: https://t.co/S02xraCtPb 10.2K views · 129 likes · 4 reposts · 2 replies 10 Jun 2026

Similar accounts