SShortSingh.
TopTechnologyAI & MLStartupsProgrammingScienceBusinessFinanceCrypto & Web3World
Back to feed
Programming

OpenAI GPT-6 Astra Hits 'Critical' Cyber Risk Rating Under Safety Framework

0
·6 views

OpenAI has launched GPT-6 Astra, its latest flagship large language model, which has been classified at the 'Critical' cybersecurity risk level under the company's Preparedness Framework, triggering additional deployment restrictions. Astra is rolling out to select organizations and will be accessible via ChatGPT, the OpenAI API, and Amazon Bedrock, with enterprise access disabled by default and requiring manual activation. In benchmark testing, Astra scored 100% on ExploitBench and 42.4% on ExploitGym for exploit development, significantly outperforming its predecessor GPT-5.6 Sol. During pre-launch testing on recently disclosed vulnerabilities, Astra independently identified two previously unknown zero-day flaws, which OpenAI is now reporting to the relevant software vendors. Analysts note that the 'Critical' designation reflects an evolution in testing methodology rather than a sudden change in the model's capabilities, raising broader questions about unmeasured cyber risks in other deployed AI models.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Log in to join the discussion and vote.

Log in

Related stories

0
ProgrammingDEV Community ·

Angular 19 Signals Enable Zoneless Change Detection for Enterprise Apps

Angular 19 introduces fine-grained Signals as a modern alternative to the long-standing Zone.js change detection model. Unlike Zone.js, which triggers dirty-checking across the entire component tree on every async event, Signals track exact DOM dependencies and update only the affected nodes. This approach eliminates Zone.js overhead entirely via the provideExperimentalZonelessChangeDetection() API, targeting consistent 60fps performance in data-heavy enterprise applications. Computed signals are lazily evaluated and memoized, replacing complex RxJS chains while also handling memory cleanup automatically. The shift is particularly relevant for enterprise dashboards handling live telemetry, grid streams, and complex forms where the legacy model caused frame drops and memory leaks.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Angular 19 Signals Enable Zoneless, 60fps Reactivity for Enterprise Apps

Angular 19 introduces fine-grained Signals as a modern alternative to the long-standing Zone.js change detection model. Unlike Zone.js, which triggers dirty-checking across the entire component tree on async events, Signals track exact DOM dependencies and update only the nodes that changed. This approach eliminates Zone.js overhead entirely via the provideExperimentalZonelessChangeDetection() provider, reducing memory leaks and frame drops common in large enterprise dashboards. Derived values are handled through lazy, memoized computed() functions, removing the need for complex RxJS chains like combineLatest or switchMap. The shift is particularly beneficial for applications displaying live telemetry, data grids, and complex forms that demand consistent 60fps performance.

0 comments Read more at DEV Community
0
ProgrammingDEV Community ·

Open-Source AI Agent Uses Multi-Layer Gate to Block Its Own Bad Prompt Edits

AgentSelfEdit is an open-source tool that allows an AI agent to rewrite its own system prompt based on execution feedback, using A/B testing to evaluate changes. By version 0.3.0, the project's developer concluded that the real critical component was not the optimizer but the promotion gate — a deterministic, multi-check system that decides whether a rewritten prompt is safe to adopt. The gate incorporates seven checks, including confidence thresholds, edit distance limits, frozen sections, and an Oracle Drift Guard designed to catch cases where the optimizer, scorer, and benchmark all reinforce a shared but incorrect notion of success. Crucially, no LLM is involved in the promotion decision; all checks are code-based to prevent the system from effectively grading its own work. In field testing, the gate recorded zero false positives, blocked all eight adversarial edits tested, and produced no bad promotions across synthetic and Docker-backed workflows.

0 comments Read more at DEV Community