Nano-GPT
Nano-GPT @NanoGPTcom · x · 2026-08-31 · ★★★ · archived
Cited as a source by: 2026-09-29-anthropic-glm-5-3-spread-of-cyber-capabilities
Summary
Archived text
Abliterated Model Large V2 is now on NanoGPT.
This uncensored GLM-5.3-based model has a 1M-token context window for harder reasoning, evaluations, long documents, and demanding conversations.
Quoting @abliteration_ai: Today we're releasing abliterated-model-large-v2.
Based on GLM-5.3, which is #3 on Terminal-Bench 4.0 (behind only Opus 5 and Fable), with 2× the cyber exploitation of 5.2.
We abliterated and hosted it so it does the offensive cyber, red teaming, and agent testing work other https://t.co/rVRhcEEgfI
likes 13 · replies 0 (at fetch time)
Archived 2026-10-03 via syndication.
Archived text
Abliterated Model Large V2 is now on NanoGPT.
This uncensored GLM-5.3-based model has a 1M-token context window for harder reasoning, evaluations, long documents, and demanding conversations.
Quoting @abliteration_ai: Today we're releasing abliterated-model-large-v2.
Based on GLM-5.3, which is #3 on Terminal-Bench 4.0 (behind only Opus 5 and Fable), with 2× the cyber exploitation of 5.2.
We abliterated and hosted it so it does the offensive cyber, red teaming, and agent testing work other https://t.co/rVRhcEEgfI
likes 13 · replies 0 (at fetch time)
Archived 2026-10-03 via syndication.
Related events
All posts · id: x-nanogptcom-2094527886413742275