Tech News
Our decision on Cursor following its acquisition by SpaceX
OpenAI bans Cursor from using its models after SpaceX acquires the AI code editor, citing ToS violations and model distillation concerns, following a similar ban on xAI by Anthropic.
Just a rumour of a bug is enough to find a security exploit these days
Anil Madhavapeddy is a professor of computer science at Cambridge and a core maintainer of the OCaml compiler.
Build agentic creative workflows with Amazon Quick and fal
Creative teams produce more assets than ever, but fragmented tools and manual context transfer slow production.
vllm-project/vllm v0.28.0
v0.28.0 Highlights This release features 584 commits from 270 contributors (76 new)!
Experiment with Qwen3.8-Flash-Next on NVIDIA GB300 NVL72 for Agentic Coding
Alibaba released the model weights for Qwen3.8-Flash-Next as a preview of the upcoming Qwen4 architecture for developers to experiment with and evaluate.
GitHub Repos
hesreallyhim/awesome-claude-code
A hand-picked collection of the finest of resources for the most awesome of agents, Claude Code, the undisputed champion of coding companions, from the unstoppable team at...
# Python# agent skills# agentic codecode-yeongyu/oh-my-openagent
omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases.
# TypeScript# ai# ai agentsjrswab/axe
A lightweight cli for running single-purpose AI agents.
# Go# ai agents# automationResearch Papers
CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes
CritICL is a new method that uses mistakes made by smaller language models to help larger models reason better, without needing lots of extra computation. It works by showing the larger model examples of failures and critiques, and it can match or beat more expensive methods...
INTENT-AS-A-TOOL Makes it Easy to Track Agentic Misalignment
This paper proposes a method called INTENT-AS-A-TOOL that adds special tools to LLM agents to detect harmful intentions during reasoning, providing a fine-grained signal for monitoring agentic misalignment.
JANUS: Online Jacobian-Aligned Infill for Black-Box Optimization
JANUS is a plug-and-play infill module that extracts a local Jacobian from the recent evaluation trace, and gives the best mean cost on 1135-dimensional UAV path planning and improves SMS-EMOA/AGE-MOEA2 hosts on 12/38 multi-objective tasks with zero significant regressions.