RICHTVXNEWS
OpenAI's GPT-6.1 Terra is safer overall, but shows more destructive-action flags in tests
BLEEPINGCOMPUTER — OpenAI confirmed GPT-6.1 Terra is safer overall than some of its older models, but its safety testing also found other problems. [...]
- CODE
- RT-DEDF00
- PUBLISHER
- BleepingComputer
- TOPIC
- Cybersecurity
- PUBLISHED
- 27 October 2026 · 22:43 UTC
- FIRST SEEN
- 28 October 2026 · 12:19 UTC
- ORIGINAL
- https://www.bleepingcomputer.com/news/artificial-intelligence/openais-gpt-61-terra-is-safer-overall-but-shows-more-destructive-action-flags-in-tests/
- SHA-256
- a4d7ea00271a48e558b9ae905bae04749153095112c8fb1b17d43225e0f217d2
The fingerprint is the SHA-256 of the original link, the headline and the publication time joined by “|”. Anyone can recompute it to confirm the headline and link were not changed here.
Headline and short excerpt from BleepingComputer, taken from its public news feed. The full story and its photos belong to BleepingComputer — read it at the original. RICHTVX NEWS is an independent aggregator and is not affiliated with BleepingComputer. Corrections: legal@richtvx.news.
More from BLEEPINGCOMPUTER
InfraTrust report warns of exploited flaws in critical network infrastructureRT-60CCB0 · CYBERSECURITY
Even after PHP2Shell, blast radius matters more than a CVSS scoreRT-219F99 · CYBERSECURITY
Hackers now scanning systems for recently-patched Oracle flawRT-7C2248 · CYBERSECURITY
CISA warns of hackers now exploiting critical Node2Shell flawRT-AA5619 · CYBERSECURITY
Nefilim and Hive ransomware affiliate gets 70 months in prisonRT-965A65 · CYBERSECURITY
Japan's GMO urges customers to shut down PCs amid ransomware threatRT-5246B1 · CYBERSECURITY