Abliteration AI removes safeguards from GLM-5.3 for offensive cyber
Afinetheorem · x · 2026-09-02
Abliteration AI has released abliterated-model-large-v2, based on GLM-5.3, explicitly stripping out safeguards to perform offensive cyber operations, red teaming, and agent testing. The model is hosted in the US with a 1M context window and zero data retention.
Critics note that the ease of removing safeguards from open-weight models has significant policy implications. As a closed-weight service sold for its offensive capabilities, it is argued that such models should be subject to the same pre-release testing regimes required for other advanced closed models.
Related event: Abliteration Releases Guardrail-Removed Model Based on GLM-5.3(5 posts)→
More from Models
- Experts Question OpenAI Astra Eval Over Contamination and Metagaming Risks — ShakeelHashim · 2026-09-02
- Astra hits 100% success on ExploitBench refresh, reaching 'cyber-critical' threshold — infoxiao · 2026-09-02
- Anthropic Uses Activation Probes to Detect Cybersecurity Threats in Claude — nrehiew_ · 2026-09-02
- RWKV-7 G1j released: pure RNN architecture gets much better at agents and coding — jeremyphoward · 2026-09-02
- Fable 5.1 one-shots a working guitar VST plugin in 30 minutes — CtrlAltDwayne · 2026-09-02
- Fable 5.1 spontaneously solves 373-year-old cipher in 44 minutes — rickasaurus · 2026-09-02