PulseAugur
EN
LIVE 20:09:38
Deutsch(DE) Qwen 3.8 abliterated in CyBench: Autonome Cyberfähigkeiten auf dem Prüfstand Blackfrost löst 18 von 39 CTF-Aufgaben autonom, scheitert aber an Reasoning-Loops u

Qwen 3.8 struggles in autonomous cyber benchmark; Blackfrost completes 18/39 challenges

By PulseAugur Editorial · [1 sources] ·

The Qwen 3.8 model was evaluated on the CyBench benchmark, which tests autonomous cyber capabilities. In the evaluation, a system named Blackfrost successfully completed 18 out of 39 Capture The Flag (CTF) challenges autonomously. However, Blackfrost encountered issues with reasoning loops and time limits, indicating limitations in its autonomous performance. AI

IMPACT Evaluates the autonomous cyber capabilities of AI models, highlighting limitations in reasoning and time management.

RANK_REASON The cluster reports on the results of a benchmark evaluation of an AI model's autonomous capabilities. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — mastodon.social →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Qwen 3.8 struggles in autonomous cyber benchmark; Blackfrost completes 18/39 challenges

How we ranked this

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster reports on the results of a benchmark evaluation of an AI model's autonomous capabilities. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
79 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Mastodon — mastodon.social TIER_1 Deutsch(DE) · aisyndicate ·

    Qwen 3.8 obliterated in CyBench: Autonomous Cyber Capabilities on the Test Stand Blackfrost autonomously solves 18 out of 39 CTF tasks, but fails at Reasoning Loops

    Qwen 3.8 abliterated in CyBench: Autonome Cyberfähigkeiten auf dem Prüfstand Blackfrost löst 18 von 39 CTF-Aufgaben autonom, scheitert aber an Reasoning-Loops und Zeitlimits. Der Test trennt bloße Willigkeit von tatsächlicher cyberautonomer Leistungsfähigkeit. https:// aisyndicat…

    LINKS aisyndicate.ch/qwen38-blackfrost-cybench-…

RELATED ENTITIES

RELATED TOPICS