I wonder what model was used for this. Also as far as I know Baseten does not have any abliterated models in their repertoire.

▲

smallnix 5 hours ago | parent | next [-]

The bot snippets talk claudish. I'd say Opus 5. But they must be Cyber Verification Program approved by Anthropic I suppose for the LLM not to block them.

▲

ryeights 3 hours ago | parent | next [-]

The Chinese models talk Claudlish too

▲

bearsyankees 5 hours ago | parent | prev [-]

Hate to burst your bubble but wasn't Claude......

	▲	antonvs an hour ago \| parent [-]
		Chinese Claude distillation.

▲

guessmyname 6 hours ago | parent | prev [-]

Either Mythos 5.1 or GPT 5.6 Cyber (aka. GPT Daybreak Red)

▲

PaoloBarbolini 5 hours ago | parent | next [-]

Even something like Qwen 3.8 27b could do this.

Lookup certificate transparency and continue from there https://crt.sh/?Identity=baseten.co&exclude=expired&match=IL...

▲

bearsyankees 6 hours ago | parent | prev | next [-]

Neither, actually :)

	▲	kibac 5 hours ago \| parent [-]
		Chinese? I can not imagine how a western state of the art model would follow through with such a task and not require some major trickery.

▲

NyxWulf 6 hours ago | parent | prev [-]

The writing sounds like Claude to me