Full-text search across 8005 articles. Combine with topic and date filters; results sorted by relevance.
Andrej Karpathy said he feels nervous when he has subscription left over because he hasn't maximized his token throughput, as of 2026-07 a curated list of 197 entries across five areas tracks AI token costs and waste. Th…
Security researchers have identified ANSI escape sequence injection (AESI) vulnerabilities in Model Context Protocol (MCP) servers that allow attackers to hide instructions from human reviewers while making them legible …
Tapetide has launched an MCP server for Indian stock market data, providing AI assistants like Claude and ChatGPT with real-time access to NSE and BSE data across all 8,200 listed stocks. The server offers 34 tools for s…
MenteDB, a Rust-based persistent memory database for AI systems, launches to solve context window limitations by enabling single-pass transformer models to store, retrieve, and reason over knowledge across sessions. The …
N3MO, a deterministic code intelligence tool that parses source code ASTs into a queryable knowledge graph without embeddings or LLM calls, launched on Hacker News. It enables transitive dependency mapping, blast radius …
Nika is a new open-source workflow language for AI that turns repeatable AI tasks into portable, auditable files. The tool, built as a single Rust binary, allows users to define workflows with four verbs and run them loc…
LeadShark launched Apex, a governed LinkedIn MCP server that lets AI agents operate LinkedIn accounts with paced, capped, approval-gated, and logged actions. The tool draws safety budgets from LeadShark's own infrastruct…
Cerberus, a local-first security gateway for AI coding agents, intercepts every tool call before execution, risk-scores it across four signals, and allows, audits, asks for human approval, or blocks it—all on the user's …
A developer wired an LLM as a first-class Yjs peer using y-prosemirror and the standard awareness protocol, demonstrating that AI agents break three silent assumptions in collaboration stacks: throughput, undo ownership,…
Z.ai released GLM-5.2, an MIT-licensed open-weight frontier model with 744B parameters, achieving top scores in frontend coding benchmarks and surpassing Opus 4.8. The model features a 1M-token context window, two reason…
A US export control order forced Anthropic to suspend access to its Claude Fable 5 and Mythos 5 models on June 12, 2026, marking the first government-forced takedown of a publicly deployed frontier model. The shutdown, t…
Design Delight Studio founder Robert McCullock launched DDS Vibe Academy, a hub offering 47 free AI coding masterclasses built entirely by AI agents without any human-written code, file uploads, or storefront saves. The …
A developer built Context Cloud after finding that common workarounds for AI coding tool memory—including CLAUDE.md files, shared Obsidian vaults, and context folders—fail to scale beyond a single user. The engineer conc…
A developer built a clean, reproducible academic dataset pipeline using ScholarAPI, an API that provides access to 30 million open-access papers with pre-extracted full text in structured JSON format. The pipeline uses f…
Agile V has released a framework that transforms unreliable AI agents into verifiable engineering systems by enforcing formal traceability, independent verification, and human gates before deployment. The framework requi…
Vlad Feinberg published a guide on how to land a job at a frontier AI lab focused on pretraining, emphasizing kernel-level performance work as the most direct path into the labs. The guide recommends deriving Chinchilla …
Claude Code v2.1.284, released 2026-09-28, made auto mode the default starting permission mode for interactive sessions that have no permissions.defaultMode set, routing every tool call that is not a read or an in-projec…
Cognition cut Devin pricing by 30-40% in Fusion and Normal modes, 15-20% in Ultra mode, and up to 70% for Devin Review, while its Fusion harness scored 68.8 on the Extended portion of the FrontierCode 1.1 benchmark at an…
Developer marciob released agenttab, a macOS tool that displays AI agent state as icons in terminal tab titles for Claude Code, Codex, and OpenCode. The tool maps states to icons — a blank title when the agent waits for …
Technical founder Jev published a September 21, 2026 essay arguing that product launches succeed on communication and decision speed, not engineering quality alone, citing the TypeSafe frenzy as his timing. Jev points to…