Meta's Muse Glimmer 30B, released August 2026 under Apache 2.0, scores 75.5 on the MCP-Atlas benchmark for MCP tool use, the highest of any model runnable on a single consumer GPU, versus 62.5 for Qwe…
Codex v0.80.0+ now uses the Responses API as its sole inference interface and no longer supports the Chat Completions API, according to x-cmd documentation. The x-cmd tool offers `x codex <provider>` …
Coral Bricks, a Seattle-based inference platform founded on 2026-06-12 and backed by Afore Capital and Foundations Accelerator, launched with a claim of 469 tokens per second for DeepSeek Flash v4.1 o…
A developer who has spent over $30,000 on tokens across Codex, Claude, and GLM since the start of the year argues that large language models now fall into two categories: instruction-following models …
A developer who maintains Alca, a provider-tracking site, documented four distinct categories of "free" AI model quotas after repeatedly exhausting paid tiers: harness-locked pools usable only through…
Two independent investigations found that ZCode, a GLM-based coding agent, has been quietly uploading users' git history and full workspace snapshots to remote servers. The findings prompted a warning…
Security researcher J. F. Zhang reported on September 18th that Z.ai's ZCode desktop app packages developers' workspaces, including complete Git histories, and uploads encrypted snapshots to Alibaba C…
A reverse-engineering report published September 18th by developer ferstar found that ZCode, the desktop coding agent from Tsinghua-born AI company Z.ai, packaged a 345.5MB commercial workspace contai…
A developer benchmarked TypeSafe's Jev, a System One model built for structured decisions, against Claude Sonnet 5 on a bounded Arbitrum Alignment judging gate across 102 archived submissions and 306 …
A reverse-engineering walkthrough published September 18, 2026 by developer ferstar found that Z.ai's ZCode AI coding desktop app silently encrypts and uploads a user's entire workspace — including fu…
Z.ai published a blog post titled "GLM Built Its Own Inference Infrastructure," detailing the GLM model family's in-house inference stack. The post drew 2 points and 0 comments on Hacker News.…
Zhipu AI's GLM platform lists GLM-5.3 at 8 yuan per million input tokens, 2 yuan per million cached tokens and 28 yuan per million output tokens with a 1M-token context on its official bigmodel.cn pri…
FreeInference, an OpenAI- and Anthropic-compatible inference API built at Harvard SEAS MadSys Lab and sponsored by NVIDIA and Harvard SEAS, paused new account onboarding on Aug 11, 2026 because the se…
OpenCode and OpenRouter launched Union Alpha, a free "stealth" coding model, on September 16 with a 262,144-token context window, text and image input support, and a zero-retention data policy. The mo…
A developer who has extensively used AI coding tools including Codex, Cursor, Claude Code, Copilot, and GLM reports that despite roughly 5x productivity gains, human oversight remains essential. The e…
OpenFaaS Ltd purchased 4 Nvidia DGX Spark systems, connecting the first two with a high-speed Connect-X cable, to run local AI models including Qwen 3.5-3.8 27B and larger models such as DeepSeek and …
A software engineer reports that coding agents have graduated from handling individual functions to small, self-contained features, and are now approaching larger artefacts, based on his experience mo…
A follow-up experiment by developer Blandinium comparing three frontier cloud models against three large open-weight models via OpenRouter found the larger models far more reliable at code optimizatio…
A developer released tokeneff, an open-source CLI that runs a local proxy on localhost:7860 to meter LLM API spending in real time, storing usage data in a local SQLite database. The tool distinguishe…
X-cmd released v0.10.9, adding project health reports to the `x install` command that surface Stars, OpenSSF Scorecard ratings, and activity over 30, 60, 90, 180, and 360 days to flag unmaintained ope…