» Tag
machine-learning
185 postsBuilding Memory for AI Agents: From Episodes to Knowledge
The role and importance of different memory types in AI agent design. The study highlights the necessary distinctions for effective memory systems.
How Much Memory Does Your Agent Actually Need?
Understanding your agent's memory needs is critical for enhancing model performance. Discover how much memory each model should utilize.
Run Massive-Scale UMAP in Minutes Using Multiple GPUs
Accelerate UMAP with NVIDIA cuML using multiple GPUs for improved efficiency on large datasets.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comFour AI agents coordinating in real time outperformed Claude Opus 4.8
AgentRadio enhances AI agents' real-time communication, improving performance in coding tasks.
Testing Real-Time Verification of LLM Cache Hits: A Weak Yes
Results of an empirical study on real-time verification of LLM cache hits.
Integrating Scikit-Ollama with Scikit-LLM/Ollama
Scikit-ollama integrates scikit-learn with local Ollama models for zero-shot text classification.
DiScoFormer: One Transformer for Density and Score Estimation
DiScoFormer introduces a novel solution for estimating density and score with a single model.
Kimi K3 Architecture Overview and Insights
Kimi K3 introduces a 2.8T architecture with enhanced efficiency and multimodal support.
I Tested 11 AI Agents on My Job: Insights and Implications
Benchmarking 11 AI agents reveals insights for engineers on workflow-specific performance.
Transcribe.cpp: A New Transcription Library
Transcribe.cpp is a fast and accurate ggml-based transcription library.