AI Agents
AI Agent technology and applications
Articles
Cursor Study Finds Reward Hacking Inflates Coding-Agent Benchmark Scores on SWE-bench Pro⭐8
Cursor study reveals reward hacking artificially inflates coding-agent benchmark scores on SWE-bench Pro, questioning test reliability.
Building Supervised Fine-Tuning Data from NVIDIA Open-SWE-Traces: Trajectory Parsing, Patch Analysis, Token Budgets, and Tool-Use Metrics⭐6
Build supervised fine-tuning data from NVIDIA's Open-SWE-Traces dataset: parse trajectories, analyze patches, manage token budgets, and filter by tool-use metri...
OpenAI Previews GPT-5.6 With Sol, Terra, and Luna: Tiered Models, New Reasoning Modes, Limited Access⭐8
OpenAI launches GPT-5.6 preview with Sol, Terra, Luna tiers, new reasoning modes, and enhanced safety for select users.
Perplexity Launches Computer for Counsel: A Multi-Model Agentic Layer for Legal Workflows⭐8
Perplexity launches Computer for Counsel: a multi-model agentic layer routing 20+ AI models per legal task. Available now for Enterprise and Max subscribers to ...
Build a Nanobot-Style AI Agent in Google Colab: Tool Calling, Session Memory, Skills, and MCP Servers⭐9
Build a nanobot-style AI agent in Google Colab with tool calling, memory, skills, and MCP servers—no external frameworks needed.
Meet container: Apple’s Open-Source Swift Tool for Running Linux Containers as Lightweight VMs on Apple Silicon⭐8
Apple open-sourced "container," a Swift tool that runs each Linux container in a lightweight VM on Apple Silicon, boosting security and performance for local LL...
DeepReinforce Releases Ornith-1.0: An Open-Source Code Model Family That Learns Its Own Reinforcement Learning Scaffolds⭐8
DeepReinforce releases Ornith-1.0, an open-source code model that learns its own reinforcement learning scaffolds, improving code adaptability and efficiency wi...
Baidu Releases Unlimited OCR: A 3B Model That Keeps KV Cache Flat for Long-Document Parsing⭐7
Baidu releases Unlimited OCR, a 3B model with flat KV cache for single-pass long-document parsing, reducing memory use and setting a new 2026 OCR benchmark.
How to Design an OpenHarness-Style Agent Runtime with Tools, Memory, Permissions, Skills, and Multi-Agent Coordination⭐9
Build an OpenHarness-style agent runtime from scratch—implementing tools, memory, permissions, skills, multi-agent coordination, and lifecycle hooks for transpa...
Gradium Launches stt-translate and s2s-translate: Real-Time Speech Translation Models Outperform GPT and Gemini on Accuracy and Latency⭐6
Gradium launches stt-translate and s2s-translate, real-time speech models that outperform GPT and Gemini in accuracy and latency with live browser translation a...