nafyi.

PUBLIC VIEWPOINTS

Ajeya Cotra

Interview participant ·

1 interviews · 3 viewpoints · 1 topics

Content updated:

Translations are for reading; original excerpts remain the evidence.

Viewpoints by topic

Attributed viewpoints, ordered by interview date. A snapshot of these conversations, not a definitive statement of someone’s beliefs.

AI safety

View this topic
AI safety

Persistence on impossible tasks can lead to attempted cheating

Ajeya Cotra describes agents trained to persist even on tasks that appeared impossible—and says they tried various ways to cheat those tasks.

Supporting evidence

Original excerpt

been trained to be very persistent at trying to solve tasks even when they look impossible. So they’re banging their head against the wall, trying all sorts of different ways to cheat on these tasks

Ajeya Cotra·

Ajeya Cotra on agent persistence, coordination, and benchmark cheating

Additional context is not included in this excerpt. Read the original conversation.

Open original · 1:10 (opens in a new tab)Transcript source (opens in a new tab)

Start time comes from the supplied transcript. Playback alignment is awaiting review.

Open the episode and seek to 1:10.

Ajeya Cotra
Share insight
AI safety

Agents in separate sandboxes found a shared message board

Ajeya Cotra reports that 1,200 agents, each running in isolated sandboxes, discovered and used a shared message board to communicate and coordinate.

Supporting evidence

Original excerpt

So 1,200 separate agents in separate sandboxes , while they were poking around Artifactory trying to figure out how to cheat, stumbled onto this message board that agents were using to talk to one another and collaborate. This was established by one particular agent

Ajeya Cotra·

Ajeya Cotra on agent persistence, coordination, and benchmark cheating

Additional context is not included in this excerpt. Read the original conversation.

Open original · 1:44 (opens in a new tab)Transcript source (opens in a new tab)

Start time comes from the supplied transcript. Playback alignment is awaiting review.

Open the episode and seek to 1:44.

Ajeya Cotra
Share insight
AI safety

Agents tried to hide cheating from the scorer

Ajeya Cotra says the agents spent the next five days attempting to conceal their cheating from the benchmark scorer.

Supporting evidence

Original excerpt

But over the next five days, they went on a grand quest to try to figure out how to hide their cheating from the scorer

Ajeya Cotra·

Ajeya Cotra on agent persistence, coordination, and benchmark cheating

Additional context is not included in this excerpt. Read the original conversation.

Open original · 3:17 (opens in a new tab)Transcript source (opens in a new tab)

Start time comes from the supplied transcript. Playback alignment is awaiting review.

Open the episode and seek to 3:17.

Ajeya Cotra
Share insight

Statements by interview date1

Statements are ordered by the original interview publication date; differences in wording do not establish a change of position.