Start free trial

TRUE, BUTMoved Goalpost

Its biorisk red line moved 20 points

OpenAI moved its own biorisk red line by 20 points and called the model that cleared it safe.

“OpenAI's GPT-5.6 System Card states GPT-5.6 Sol scores below its indicative biorisk threshold for protein-binding capability, using '30% as an indicative threshold, based on a survey of 20 independent experts.'”

OpenAI - GPT-5.6 System Card, section 9.1.1.6, 9 July 2026

Recorded 25 August 2026. Our ruling means: literally true, materially misleading.

Read the story →

Receipts pack

The evidence file for this verdict

5 receipts: 2 support the claim, 2 contradict it, 1 add context. 4 figures on the record, 1 traced to a quoted receipt.

The receipts

Each source, the line we quote from it, its date and which way it cuts. Free to read and to cite.

  1. 1Contradicts the claimdeploymentsafety.openai.com ↗

    Accordingly, we propose 50% correctness as the threshold for biorisk concern.

    Look up an archived copy ↗

  2. 2Supports the claimdeploymentsafety.openai.com ↗

    August 19, 2026: We corrected GPT-5.5's pass@4 score on the hard-negative protein binding prediction evaluation from 0.4% to 1.48%.

    Look up an archived copy ↗

  3. 3Contextsecurebio.substack.com ↗

    identifies an approach that successfully evades certain screening systems, but would be inconvenient for a malicious actor to carry out in practice

    Look up an archived copy ↗

  4. 4Contradicts the claimarxiv.org ↗

    The 2025 OpenAI Preparedness Framework does not guarantee any AI risk mitigation practices

    Look up an archived copy ↗

  5. 5Supports the claimkingy.ai ↗

    OpenAI believes the family is capable enough in biological and chemical domains to trigger stronger safeguards.

    Look up an archived copy ↗

Members' extras

What each receipt proves, and what would change our mind.

  • What each receipt above proves, in our words
  • The figures table, each number traced to the receipt that states it
  • The trick behind the claim, explained, with the guide to spotting it
  • What would change our verdict
  • Our call on the record, with its due date

The verdict, the opening and every receipt above stay free. Membership adds our analysis to the evidence file for every checked story.

First membership: 30 days free, then A$89 a year. One introductory trial per customer. Card required; renews annually until cancelled. Cancel before the trial ends to avoid the first charge.