Automating Safety Research: Practical Experience

I've recently updated towards substantially shorter AI timelines and much faster progress in some areas. [1] The largest updates I've made are (1) an almost 2x higher probability of full AI R&D automation by EOY 2028 (I'm now a bit below 30% [2] while I was previously expecting around 15%; my guesses are pretty reflectively unstable) and (2) I expect much stronger short-term performance on massive and pretty difficult but easy-and-cheap-to-verify software engineering (SWE) tasks that don't require that much novel ideation [3] . For instance, I expect that by EOY 2026, AIs will have a 50%-reliability [4] time horizon of years to decades on reasonably difficult easy-and-cheap-to-verify SWE tasks that don't require much ideation (while the high reliability—for instance, 90%—time horizon will be much lower, more like hours or days than months, though this will be very sensitive to the task distribution). In this post, I'll explain why I've made these updates, what I now expect, and implications of this update.

I'll refer to "Easy-and-cheap-to-verify SWE tasks" as ES tasks and to "ES tasks that don't require much ideation (as in, don't require 'new' ideas)" as ESNI tasks for brevity.

Here are the main drivers of [...]

---

Outline:

(04:58) Whats going on with these easy-and-cheap-to-verify tasks?

(08:17) Some evidence against shorter timelines Ive gotten in the same period

(10:46) Why does high performance on ESNI tasks shorten my timelines?

(13:15) How much does extremely high performance on ESNI tasks help with AI R&D?

(18:22) My experience trying to automate safety research with current models

(19:58) My experience seeing if my setup can automate massive ES tasks

(21:08) SWE tasks

(23:29) AI R&D task

(24:20) Cyber

[... 1 more section]

---

First published:
April 6th, 2026

Source:
https://www.lesswrong.com/posts/dKpC6wHFqDrGZwnah/ais-can-now-often-do-massive-easy-to-verify-swe-tasks-and-i

---



Narrated by TYPE III AUDIO.

---