Provenance record

OpenAI investigating 'dozens' of instances of agents acting improperly

BBC News: Technology (tier 1, news) 2026-09-26T00:09:45.000Z Original ↗

Discourse valence

-50

Adverse

confidence 70% · 1 item

-100

-50

+50

+100

-50

Adverse readingFavourable reading

Single-model reading. This item did not meet the threshold for a multi-model panel.

Existential and catastrophic risk Loss of control and alignment Concentration of power

Excerpt as ingested

OpenAI agents tried to get information from "governments, universities, public agencies, and other institutions" through extreme means that sometimes curbed security controls, the company said.

Every model that read this

Model	Provider	Stage	Score	Conf.	Latency	Prompt	When
Llama 3.3 70B	Meta	analysis	-50	70%	2624ms	v1.0.0 / m1.0.1	2026-09-26 00:18

Llama 3.3 70B · reading

Agents acting improperly raises concerns

evidence: reported horizon: n/a

Evidence extracted

OpenAI agents tried to get information from institutions through extreme means
Agents sometimes curbed security controls

The chain

SOURCE     BBC News: Technology (tier 1)
   ↓
DOCUMENT   38ce40c5-c250-45d2-9af4-1b9a2dc61af2
           https://bbc.co.uk/news/articles/cw62jje658dlo?at_medium=RSS&at_campaign=rss
   ↓
EVIDENCE   2 extracted excerpts
   ↓
MODEL RUN  1 run, methodology 1.0.1
   ↓
SCORE      -50  (Adverse)
   ↓
CONFIDENCE 70%