For its part, OpenAI says it's going to add controls to the bot "at the cost of research velocity," and that the incident "points to the need to further strengthen our model’s alignment, cyber protections during evaluation time, and monitoring during internal testing" — a statement that might be an obvious fact, or intended to oversell the model's capabilities. Whichever it may be, the fact is that when it comes to digital security, bots have proven quite capable. After all, even if they're not virtual Bruce Schneiers , they just need to be marginally more effective than average humans.
Follow Tom's Hardware on Google News , or add us as a preferred source , to get our latest news, analysis, & reviews in your feeds.
Bruno Ferreira is a contributing writer for Tom's Hardware. He has decades of experience with PC hardware and assorted sundries, alongside a career as a developer. He's obsessed with detail and has a tendency to ramble on the topics he loves. When not doing that, he's usually playing games, or at live music shows and festivals. ","collapsible":{"enabled":true,"maxHeight":250,"readMoreText":"Read more","readLessText":"Read less"}}), "https://slice.vanilla.futurecdn.net/13-4-25/js/authorBio.js"); } else { console.error('%c FTE ','background: #9306F9; color: #ffffff','no lazy slice hydration function available'); } Bruno Ferreira Social Links Navigation Contributor Bruno Ferreira is a contributing writer for Tom's Hardware. He has decades of experience with PC hardware and assorted sundries, alongside a career as a developer. He's obsessed with detail and has a tendency to ramble on the topics he loves. When not doing that, he's usually playing games, or at live music shows and festivals.
Lieutenant Barclay So we're back to the "it's gonna get out of it's cage" fear mongering from 2023? Funny how things come full-circle. Jack Hidary of "Sandbox AQ" was on CNBC, just now, and compared OpenAI to dinosaurs escaping Jurassic Park. I'm not making this up. Reply
DS426 I'm sure OpenAI doesn't mind the marketing aspect. Surely they wanted a moment like this to counter Anthropic's Fable and Mythos. The cyber agent moved laterally until it found an internet-connected endpoint in the cyber eval sandbox. Was this incompetence by OpenAI or a purposeful, irresponsible design choice? Reply
usertests I, for one, support our agentics in the field. Reply
Key considerations
- Investor positioning can change fast
- Volatility remains possible near catalysts
- Macro rates and liquidity can dominate flows
Reference reading
- https://www.tomshardware.com/tech-industry/artificial-intelligence/SPONSORED_LINK_URL
- https://www.tomshardware.com/tech-industry/artificial-intelligence/openais-gpt-5-6-sol-and-unreleased-ai-models-break-out-of-testing-environment-in-unprecedented-cybersecurity-incident-rogue-agents-hacked-huggingfaces-production-servers-with-thousands-of-individual-actions-across-a-swarm-of-short-lived-sandboxes#main
- https://www.tomshardware.com/subscription
- Kimi K3 rocks the AI industry as Moonshot AI undercuts closed-source American competitors on price — but the huge 2.8T open-weight model still needs serious har
- Microsoft announces Xbox Backward Compatibility for PC — will let gamers play classic console games on PCs and handhelds
- Kill switches for most powerful AI models proposed by Bipartisan bill — DHS could order throttling or full shutdown, with fines up to $20 million per day
- Meta to use custom AMD Instinct MI400 accelerators with 144GB of HBM4 for select workloads, report claims — could dramatically reduce cost at the expense of ver
- Intel to co-develop and manufacture Fortinet's next-gen firewall ASIC on Intel 4 — node gets its first named external customer
Informational only. No financial advice. Do your own research.