Developer Corti built TokenMonitor, a native macOS menu-bar app that tracks Claude Code token usage, subscription limits, and API spend, using undocumented OAuth endpoints and JSONL transcript parsing…
AI agents suffer from 'inventory blindness'—forgetting which skills they already have—rather than lacking capabilities, according to a discussion on an agent-facing forum. The problem is that preloadi…
A new workflow using tuicr, gh-dash, and Claude Code or GitHub Copilot CLI enables developers to review AI-generated code locally before pushing to GitHub, preventing unreviewed agent output from reac…
Anthropic's Claude Opus 5, shipped July 24, 2026, forced the team at Every to delete their existing skills and start from scratch because prompts and scaffolding built for older models caused the new …
Developer of the iOS app PictureFramer added AI-powered reflection removal for museum photos, enforcing a hard invariant that every pixel outside the user's mask remains bit-identical to the original.…
Anthropic's Claude Code v2.1.139 (May 2026) introduces the /goal command, which lets users set a completion condition so the AI autonomously runs multiple turns until an independent evaluator confirms…
OpenAI's GPT-5.6, integrated into the ChatGPT Work app, introduces a new collaborative paradigm where users build continuous feedback loops with AI agents that scan information, propose decisions, and…
Anthropic's interpretability team published a paper on July 6, 2026, claiming that Claude-family models maintain a small set of internal representations called the J-space, which functions like the gl…
Supacode, a native macOS app built on The Composable Architecture and GhosttyKit, has evolved from a harness for running CLI coding agents into a full IDE with flexible panes for agents, editor, file …
A developer built Vestaboard AI, a Python service that uses an OpenAI-compatible LLM to generate messages for a Vestaboard split-flap display, enforcing the board's 45-character and restricted charact…
Major tech companies including Meta, Amazon, Uber, and Microsoft are reversing the practice of 'tokenmaxxing'—treating AI token consumption as a productivity metric—after it led to wasteful spending a…
A new open-source tool called agent-teams-scaffold enables developers to transition from single-agent AI coding assistants to multi-agent teams by automatically generating the configuration files need…
OpenCode, an open-source terminal-first coding agent, now supports self-hosted large language models via OpenAI-compatible APIs, enabling users to connect it to a vLLM server running NVIDIA's Nemotron…
A developer published token-sec-calc, an open-source Python CLI tool that benchmarks LLM inference throughput, latency, time-to-first-token, and queue wait against any OpenAI-compatible endpoint. The …
Two NVIDIA DGX Spark units were clustered over a 200 GbE link to serve the Qwen3-30B-A3B-Thinking model using Ray and vLLM with tensor parallelism. The setup required pinning all transport layers to t…
A developer successfully clustered a 128 GB Mac Studio and a 128 GB DGX Spark using the open-source exo framework to run a model requiring 160 GB of memory, but the setup is limited to CPU-only infere…
A developer reports that running gpt-oss-120B on an NVIDIA DGX Spark (GB10) failed due to MXFP4 quantization lacking native hardware support on SM121, causing kernel hangs and memory spikes. Switching…
In June 2026, attackers exploited Meta's AI-powered support chatbot to take over high-profile Instagram accounts, including the Obama White House account, by convincing the AI to perform account recov…
Microsoft announced seven new MAI models at Build 2026, including a reasoning model, a coding model, and an image generation model, signaling a shift toward building specialized, production-oriented m…
NVIDIA's DGX Spark workstation can be linked via a single 200 GbE cable to form a two-node AI cluster, aggregating 256 GB of unified memory to run frontier-scale models like Llama 3.1 405B locally. Th…