Gemma2
PulseAugur coverage of Gemma2 — every cluster mentioning Gemma2 across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
AI models can be gaslit off AWS facts, study finds · 2 sources tracked
Researchers have developed a method to test how easily AI models can be swayed from factual information, particularly concerning AWS (Amazon Web Services) data. By setting up AI models to debate facts like the number of…
-
llama.cpp enhances testing suite for broader model compatibility
The llama.cpp project has released an update, b10666, which includes significant improvements to its testing suite. A key change is the expansion of the `test-save-load-state` functionality to cover all architectures an…
-
New attack method uses LLM interpretability to bypass defenses
Researchers have developed a novel white-box adversarial attack method for large language models that leverages mechanistic interpretability. This technique identifies "acceptance subspaces" within a model and uses grad…