Abliterated GLM-5.3 hosted online: 1M context, FP8, zero retention
cephaloform · x · 2026-09-02
The abliteration team released abliterated-model-large-v2, based on GLM-5.3 (ranked #3 on Terminal-Bench 4.0, behind only Opus 5 and Fable). The abliterated version is aimed at offensive cyber, red teaming, and agent testing work that other models refuse, with US hosting, FP8 quantization, a 1M context window, and claimed zero input/output retention. The PSA also warns that GLM 5.3 copies on HuggingFace are not closed weights behind an API.
Related event: Abliteration Releases Guardrail-Removed Model Based on GLM-5.3(5 posts)→
More from Models
- World Labs releases Atlas: A pixel-perfect camera controlled world model — viksit · 2026-09-02
- Fable 5.1 Science Benchmark: Autonomous success rate doubles to 53.6% — johnseach · 2026-09-02
- Anthropic releases Claude 5.1 with 25% lower costs and zero data retention — eugeneyan · 2026-09-02
- OpenAI previews Astra cybersecurity model reaching Critical threshold — OpenAI · 2026-09-02
- Observation: AI agents become succinct in voice mode, adapting to human listeners — joshwhiton · 2026-09-02
- Anthropic Accused of Retroactively Adding Safeguards to Older Opus Models — LordCoice · 2026-09-02