gemma3:12b
PulseAugur coverage of gemma3:12b — every cluster mentioning gemma3:12b across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Personas shape LLM agent behavior in strategic games
Researchers investigated how persona prompts influence the strategic behavior of large language model agents in a "Split or Steal" game. Using four open-source models (Ministral-3-3B, phi4:14b, Gemma3:12b, and Gemma4:e4…
-
Open-source LLMs show promise for privacy-preserving clinical decision-making assessment
A new study, LLM4SDM, investigates the use of open-source smaller language models (OS-sLLMs) for assessing shared decision-making (SDM) in clinical consultations. Unlike previous research that utilized large commercial …
-
LLMs fail to replicate human mental imagery structure, study finds
A new study published on arXiv reveals that large language models (LLMs) fail to replicate the relational structure of mental imagery found in human populations. Researchers analyzed vividness ratings from distinct huma…
-
AI model quality metrics fail as safety proxies under quantization
A new research paper challenges the common practice of using quality metrics as a proxy for safety in quantized AI models. The study found that quality can remain stable or even improve while safety metrics, such as ref…
-
AI agent's background tasks consumed 603M tokens; developer implements routing
An AI developer discovered that their Hermes Agent was consuming a significant number of tokens, totaling 603 million over seven days, due to silently running background tasks. The issue was traced to the kimi-k2.6 mode…
-
New GRADE framework evaluates AI tutor pedagogical abilities
A new research paper introduces GRADE, a framework for evaluating the pedagogical capabilities of AI tutors. The study systematically assessed 120 configurations of five language models, exploring methods like zero-shot…