Checked fact 102112 Oct 2026Research

Epoch says: "Despite spending thousands of dollars on GPU usage, neither AI model achieved a result close to on-policy self-distillation, either conceptually or in terms of performance on metrics." The models were Claude Fable 5 and GPT-5.6 Sol.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

Despite spending thousands of dollars on GPU usage, neither AI model achieved a result close to on-policy self-distillation

What the source said when we opened it, on 12 Oct 2026.

The source

Can AI automate AI R&D yet?
Epoch AI · 2026-10-07

Open the source archived copy

Checked

Checked by the notis newsroom on 12 Oct 2026, against the source above.

In the story

Epoch AI says frontier models given about 3,000 GPU-hours did not rediscover a recent post-training method. 12 Oct 2026

Cite this fact

Short permanent address

In a sentence

“Epoch says: "Despite spending thousands of dollars on GPU usage, neither AI model achieved a result close to on-policy self-distillation, either conceptually or in terms of performance on metrics." The models were Claude Fable 5 and GPT-5.6 Sol.” ai notis, checked 12 Oct 2026. Source: Can AI automate AI R&D yet? (Epoch AI). https://ainotis.com/c/1021

As a reference (APA style)

ai notis. (2026, October 12). Epoch says: "Despite spending thousands of dollars on GPU usage, neither AI model achieved a result close to on-policy self-distillation, either conceptually or in terms of performance on metrics." The models were Claude Fable 5 and GPT-5.6 Sol [Checked claim 1021]. ai notis. https://ainotis.com/c/1021

Anyone may quote this address. It does not change; if we correct the story, this page says so.