NewsNature

Heuristic editor, no API keyVerdict: Routine

I told ChatGPT to 'continue' — it went too far

Original title: I told ChatGPT to ‘continue’ — it went too far

An ambiguous instruction caused the chatbot to send three e-mails from Ying Zhao's connected account.

By Zhao

Score████░░░░░░3.9

VerdictCompetent work. Briefs at most.

Read at Nature

Summary from the source

An ambiguous instruction caused the chatbot to send three e-mails from Ying Zhao’s connected account. The incident advanced Zhao’s project, but showed that chatbots need limits.

Ying Zhao

The editor's rubric

Heuristic review

DimensionLevelWeightWhat that level means
Leverage██░░░ 215%Reusable within one subfield (a technique, dataset, or protocol a few groups will adopt).
Magnitude██░░░ 220%Solid incremental gain on a meaningful problem.
Evidence██░░░ 220%Limited: single setting, weak baselines, or an observational association presented as causal.
Novelty██░░░ 210%A new combination of known ideas.
Trajectory██░░░ 210%Some room to improve with obvious engineering.
Stakes██░░░ 225%Benefits a professional community (practitioners, clinicians, engineers).

Editor’s rationale

Heuristic triage from title and abstract text only, not a reading of the paper. No strong cues found.

How the score was computed

rank-2026-10-07

Score████░░░░░░3.9

Score = 10 × (50% × adjusted merit / 10 + 25% × attention + 25% × freshness)

Merit
3.4 / 10
Weighted rubric, evidence-gated.
Adjusted merit
3.8 / 10
Shrunk toward the desk prior by editor confidence (30%).
Attention
31%
Citations, upvotes, points, mentions.
Freshness
49%
Half-life decay since publication.

No attention signals recorded yet.

The record

  • Reviewed by heuristic-v6 on Oct 12, 2026, 18:45 UTC. Paper type: news.
  • BRIEF, No.7 in the News edition of October 12, 2026.