• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
• fine-tuning — Taking a trained model and training it a bit more on your own examples so it gets better at one specific job.

Large tool catalogs inflate latency and cause wrong tool picks. A small late-interaction retriever in front of the model keeps context short and selection accurate without any fine-tuning.

• postDSpark draft models cut LFM2.5 agent latency roughly in half
• postTwo 350M retrieval models: one dense, one late interaction
• postPipette benchmarks local models as model, quant, runtime and device
• postLiquid AI's 230M model runs agentic tool calls on a Raspberry Pi

• postTwo 350M retrieval models: one dense, one late interactionLiquid AI
• postLiquid AI's 230M model runs agentic tool calls on a Raspberry PiLiquid AI
• postLFM2.5-VL-3B reads screens and grounds objects inside 3GBLiquid AI

Checking sign-in…

Loading comments…