Model distillation: How a small AI learns from a bigger one, and why it is disputed
Distillation trains a small, cheap AI model on the answers of a bigger one. It is a standard technique, and also the…
Research
AI research in plain English: new studies and breakthroughs in mathematics, medicine, neuroscience and computing, and what they mean outside the lab.
Advertisement
More News
Explore more stories from Aiholics News
Claude wrote quantum circuits that beat published designs on all eight tasks
Anthropic says Claude Mythos 5 designed circuits for eight quantum tasks that use fewer qubits and gates than…
AI agent harness: The setup around a model that decides how well it works
An agent harness is everything around an AI model: prompts, tools, memory and rules. Why the same model…
Speech-to-speech models: How voice AI listens and talks without turning speech into text
A speech-to-speech model takes in audio and replies in audio with a single model. Here is how it…
NVFP4: How 4-bit numbers let huge AI models fit in far less memory
NVFP4 is Nvidia's 4-bit number format for AI models. Each group of 16 values shares a scale factor,…
AI agent memory: How a chatbot learns to remember you between conversations
AI agent memory lets an assistant write notes outside its short-term context and read them back in later…
The CPU bottleneck in agentic AI: Why AI agents keep processors busy while GPUs wait
AI agents spend much of their time running tools, not generating text. That work lands on CPUs, and…
Time-series foundation models: How one pretrained model forecasts data it has never seen
A time-series foundation model is pretrained once on huge amounts of sequence data, then forecasts new series zero-shot.…
Speaker diarization: How AI works out who said what in a recording
Speaker diarization labels every stretch of a recording with the person talking. It is what lets a meeting…