Phi-3.5
PulseAugur coverage of Phi-3.5 — every cluster mentioning Phi-3.5 across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New PRISM method detects physical dangers in LLM actions beyond text safety
Researchers have developed a new method called PRISM to detect physical dangers posed by large language models (LLMs) when they are used to control embodied agents. Unlike traditional text-based safety checks, PRISM ana…
-
iOS app GenBench enables on-device GGUF model benchmarking
A new free iOS application called GenBench has been released, allowing users to download, run, and benchmark GGUF models directly on their iPhones and iPads. The app utilizes llama.cpp and Metal for offline operation an…
-
KV cache eviction protection proves more vital than scoring
Researchers have developed a new method for managing KV cache eviction in large language models, finding that structural protection is more critical than scoring algorithms. Their study on transformer models revealed th…