Tech News
Saving Jet Fuel
A Hacker News discussion examines the gap between simple fuel-optimal flight planning and commercial tools that account for ATC routing, crew costs, and congestion.
commit-rewriter 0.1
I built this little web app the other day to help edit the commit messages for the Datasette security releases.
Your Agent Aced the Task. Will It Do It Again?
IBM Research introduces ALTK-Evolve, a method for measuring and improving how consistently AI agents repeat successful task performance.
Abnormal AI: Amazon Bedrock AgentCore for agentic email security at scale
Learn how Abnormal AI deployed Amazon Bedrock AgentCore Code Interpreter as an ephemeral compute scratch pad for the agents behind its real-time email threat detection at billion-message scale, plus the sandbox design...
vllm-project/vllm v0.29.0
v0.29.0 Highlights This release features 594 commits from 277 contributors (91 new)! Model Runner V2 is now the default for all models (#53183), completing the rollout that began with pooling models (#48290).
GitHub Repos
diegosouzapw/OmniRoute
Never stop coding.
# TypeScript# a2a# ai agentssickn33/agentic-awesome-skills
AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,115+ agentic skills.
# Python# agent skills# agentic skillsjrswab/axe
A lightweight cli for running single-purpose AI agents.
# Go# ai agents# automationResearch Papers
Towards Detecting AI-Assisted Responses in Online Surveys
This paper creates a benchmark to test how well we can detect AI-written survey responses. It finds that simple AI use is easy to catch, but AI agents pretending to be specific people are much harder to detect, and proposes a simple method to improve detection.
FluxVLA Engine: A One-Stop VLA Engineering Platform for Embodied Intelligence
FluxVLA Engine is an open-source, configuration-driven platform that standardizes the messy engineering pipeline for embodied AI—from datasets and training to simulation evaluation and real-robot deployment. It does not propose a new policy model; instead, it tries to make...
SlotDiT: Object-Centric Representations for Diffusion Transformers
SlotDiT is a new text-guided diffusion transformer that predicts future scene dynamics using object-centric slots instead of pixel-level latents, aiming to improve robotic video generation.