Tech News
Claude Code sends 33k tokens before reading the prompt; OpenCode sends 7k
A study finds Claude Code uses significantly more tokens than OpenCode due to inefficient caching and sub-agent spawning, with 33k vs 7k tokens sent before reading the prompt.
Directly Responsible Individuals (DRI)
I went looking for a definition of "Directly Responsible Individuals" and the best I found was in the GitLab handbook. Apparently the term originated at Apple, where it's used to describe the person who is "ultimately.
Accelerating End-to-End Co-Folding Performance with NVIDIA BioNeMo Agent Toolkit
Biomolecular structure prediction and co-folding with models like OpenFold3 are now mainstream, large-scale workloads powering drug discovery and protein.
Build a semantic layer for agentic AI on AWS with Stardog and Amazon Bedrock AgentCore
In this post we show how to build a semantic layer on AWS using Stardog’s Semantic AI Application over Amazon Aurora and Amazon Redshift, and how to run a Strands Agents agent on Amazon Bedrock AgentCore that queries.
How Deutsche Telekom is rewiring telecommunications with AI
How Deutsche Telekom is becoming an AI-native telco with OpenAI-transforming customer service, employee workflows, network operations, and the future of voice.
GitHub Repos
opendatalab/MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
# Python# ai4science# document analysislabring/FastGPT
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, and visual AI...
# TypeScript# agent# claudejgravelle/jcodemunch-mcp
Cut AI token costs 95%+ on code exploration.
# Python# ai coding# ai toolsResearch Papers
UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks
UniClawBench is a new benchmark for evaluating proactive AI agents on real-world tasks, using live Docker containers and a capability-driven design to isolate agent failures.
Toward Active Object Detection for UAVs in the Wild: A Large-Scale Dataset, Benchmark and Method
This paper presents a large-scale dataset and benchmark for active object detection from UAVs, and proposes a method using JEPA to improve state representation learning.
Parameter-Efficient Vision-Language Adaptation with Continuous Metadata Conditioning for Animal Re-Identification
This paper proposes a method to adapt CLIP, a vision-language model, for long-term animal re-identification by incorporating continuous metadata (like age or weight) directly into prompts, avoiding discretization into text categories.