cc-tap is an experiment that connects Desktop and Code sessions using the undocumented Remote Control API.
Cal.com has stopped disclosing its source, citing the rise of AI-driven vulnerability discovery.
Claude's Rate Limits have been permanently raised.
Open-sourced a web-search Research agent and a document chatbot Support agent.
Swapped Qwen 1.5B's decoder head with a CHIP-8 opcode head and ran it directly.
A benchmark running MiniMax M2.7 AWQ on 8x MI50 32GB hit a peak of 64 tok/s.
Codex received a major update spanning computer use, browser control, and even image generation.
A human-first code review tool that breaks PRs into chapters to read
Unlike general-purpose benchmarks, Opus 4.7 scored lower than 4.6 in a real-world workflow.
Claude Opus 4.7 removes manual thinking settings and supports only adaptive thinking.
In Open WebUI with OpenUI attached, gpt-5.4-mini responded the fastest.
Manual extended thinking has disappeared in Opus 4.7, leaving only adaptive thinking.
It compresses the context of each LLM call into a Manifest to auto-bootstrap the evaluation stack.
A local agent memory engine that re-weights memories based on failure/success feedback.
A summary of the performance and limitations of local music generation on Apple Silicon by running ACE-Step 1.5 with MLX.
By combining camera-controlled video generation with 3D reconstruction, it creates persistent, explorable 3D worlds.
Qwen3.6-35B-A3B produced a better pelican SVG than Claude Opus 4.7 on a local laptop.
On refined data, 1.7B beat 744B, but noisy traces collapsed performance.
Released WhereMyTokens, a Claude Code token monitor for Windows.
LangSmith has released reusable Evaluators and a library of 30+ templates to improve agent evaluation efficiency.
A proposal has been raised to reduce the Qwen Code OAuth free tier and end it on April 15.
Job Bro v0.1.5 privately analyzes LinkedIn JDs using a local LLM.
A new `seven_day_omelette` quota has been added to Claude.ai's usage API.
Meta used common tools and skills to automate the detection and fixing of performance issues with AI agents.