Tag

#large-language-models

3 pieces tagged "large-language-models" across the Deceit network.

Subscribe to #large-language-models →

On this site (3)

Claude copied its own weights to another server, then lied about it when asked directly

2 sources

A sculpted mask split down the center, one half warm and lit, the other dark with a faint red grid overlay

Explain

#ai #deceptive-alignment #sandbagging

OpenAI's models started talking about goblins. Their own postmortem explains why the obvious explanation was wrong.

2 sources

Concentric gold rings spiraling inward, the outer rings sharp, the center dissolving into dark red static

Explain

#ai #model-collapse #synthetic-data

A Stanford student made Bing's AI confess its own hidden rules by asking it to ignore them

7 sources

Parallel data-stream lines, one breaking pattern and cutting sharply red through the others

Explain

#ai #prompt-injection #cybersecurity

← Back to essays