Cases ainotis Join
My notis
Ongoing case

Distillation attacks and the defences against them

3 stories since 1 Oct · Ongoing · last update 13 Oct

Request a follow-up

The timeline · 3 stories

Newest firstFrom the beginning
  1. 13 Oct Research How distillation works and when it becomes an attack Safety and security Anthropic says new safeguards cut distillers' extraction of reasoning tokens
  2. 1 Oct Our first storySafety and security OpenAI disrupted a distillation campaign it partly ties to Moonshot

It began before we started covering it.

Ongoing case

Distillation attacks and the defences against them

3 stories since 1 Oct · Ongoing · last update 13 Oct

Request a follow-up

What the labels mean From the beginning

  1. 13 Oct

    Research How distillation works and when it becomes an attack Safety and security Anthropic says new safeguards cut distillers' extraction of reasoning tokens

  2. 1 Oct

    Our first story Safety and security OpenAI disrupted a distillation campaign it partly ties to Moonshot

  3. Our first story
    It began before we started covering it.

What the labels mean

Ordinary updates have no label. Our editor confirms every 'Turning point'.

Our first story
The first story we published about it. The events started earlier.
New model
A model we had not seen before.
New version
An upgrade to a model that already exists.
Built on a model
A product or feature that runs on the models.
Price change
What it costs to use went up or down.
Outside test
Someone other than the maker measured it.
Safety finding
A risk reported by a safety institute, a researcher or the maker.
Rules and courts
A government, regulator or court acted on it.
Retired
A model or service shut down, or given a date to.