Latest in Llm
Sort by
7 items
-
How custom evals get consistent results from LLM applications
Public benchmarks are designed to evaluate general LLM capabilities. Custom evals measure LLM performance on specific tasks.Tech - VentureBeat - November 14 -
How Microsoft’s next-gen BitNet architecture is turbocharging LLM efficiency
A smart combination of quantization and sparsity allows BitNet LLMs to become even faster and more compute/memory efficientTech - VentureBeat - November 14 -
Here are 3 critical LLM compression strategies to supercharge AI performance
How techniques like model pruning, quantization and knowledge distillation can optimize LLMs for faster, cheaper predictions.Tech - VentureBeat - November 9 -
Puppygraph speeds up LLMs’ access to graph data insights
While PuppyGraph is less than a year old, it is already witnessing success with several enterprises, including Coinbase, Clarivate, Dawn Capital and Prevelant AI.Tech - VentureBeat - November 7 -
Why multi-agent AI tackles complexities LLMs can’t
While AGI and fully autonomous systems are still on the horizon, multi-agents will bridge the current gap between LLMs and AGI.Tech - VentureBeat - November 2 -
Study finds LLMs can identify their own mistakes
It turns out that LLMs encode quite a bit of knowledge about the truthfulness of their answers, even when they give the wrong one.Tech - VentureBeat - October 29 -
DeepMind and Hugging Face release SynthID to watermark LLM-generated text
SynthID makes subtle changes to LLM-generated text to create a statistical signature while preserving the quality of the output.Tech - VentureBeat - October 25