Full-text search across 68361 articles. Combine with topic and date filters; results sorted by relevance.
Cua released CUA-S1, a family of small, specialized "System 1" models for computer-use decisions, alongside open-source desktop automation tools including Cua Fleets, Cua Driver, Lume, and Cua Bench. Cua Driver lets agen…
Steve Yegge's essay "The Flat Curve Society" argues that commodity AI intelligence is flattening and that organizations should measure token waste rather than token spend, according to a post analyzing the shift. The pos…
A developer-penned guide outlines a verification workflow for evaluating self-hosted LLM tool specifications before integration, focusing on license files, hardware requirements, and true offline capability. The guide re…
A developer argues that the decisive factor in whether AI code review works on GitHub is the integration mechanism connecting the tool to pull requests, not the underlying model or vendor feature comparisons. Citing Grap…
A census of 20 AI agents and platforms from Google, Microsoft, AWS, OpenAI, Anthropic, GitHub, Cloudflare, Slack and Cursor found that 11 give the agent its own principal while 9 reuse the user's login, according to the …
SemiAnalysis reported that DeepSeek's Engram architecture, which extends standard token embeddings with learned multi-token lookups, can lower required HBM capacity for models at the same quality by offloading embedding …
A 2026 cost analysis from LaunchDay Advisors finds that building a partner-developed MCP server runs roughly $100K–$300K for a level-1 read-only, single-client connector, $300K–$700K for a level-2 actions server, and $1M…
A developer ported a 2,150-line bash agent that orchestrates command-line tools, calls a model, and reshapes JSON into 2,258 lines of Python, finding that the rewrite cut actual code by 40% while adding comments and docs…
Developer Parvej Shah argues that AI-assisted development has made software creation dramatically faster, but warns that shipping speed is not the same as usability. He contends the real promise of rapid prototyping is s…
A developer released codsh 0.23.0, a DeepSeek-native terminal coding agent built on the open dsh harness, introducing a Mission Contract control plane for its /ship command. The contract compiles sealed acceptance criter…
A single-file Claude Code agent built on Opus 5 scored 0.9505 on the gNucleus Parametric CAD Bench, with 89 of 100 parts scoring a perfect 1.0 and running 37% cheaper than the prior top row on the public leaderboard. The…
Google, Google DeepMind, the University of Maryland, and the University of Virginia published a 2026 technical report describing Dream-RSI, a method that optimizes AI agent search strategies offline by replaying past dis…
A developer argues that the cost of loop-based agentic coding is driven by the verification surface under the agent rather than token prices, since loops run unattended, long, and in parallel. The analysis holds that tot…
A developer built x-skills-daily-reflection, a scheduled job that runs at 05:00 daily on top of the xskills agent-skill collection to scan the last 24 hours of AI coding agent sessions for friction and propose edits to t…
Weave is experimenting with whether a market of AI agents trading on a central limit order book can price a pull request's impact or utility, using the company's "code output" metric — one unit equal to one hour of an ex…
A developer has outlined a method for running autonomous AI coding agents safely on Apple Silicon Macs by isolating agent execution inside a Linux VM while keeping model inference on the macOS host, working around Virtua…
Palo Alto Networks' Unit 42 reported that a human attacker used AI agents to breach an unnamed European IT and software company in under 10 hours during summer 2026, an operation Unit 42 estimated would ordinarily take h…
TypeSafe AI, a stealth-stage startup founded by former OpenAI researcher Diogo Almeida, released Jev on September 15, a non-autoregressive model that generates no text and instead returns full probability distributions o…
Tron founder Justin Sun announced the "Justin Sun Prize" on X on September 16, offering up to $1 million per "Pinnacle" mathematics problem to whoever solves it first, with no distinction between human and AI-generated p…
A developer built a custom monitoring script, daily_check.py, to audit their AI trading bots and found the equities bot skipped 28 trades in a single session due to budget constraints, filling only 8. The bot attempted t…