A collection of 71 posts
Google's Gemini 3.5 Live Translate is a new audio model for continuous speech-to-speech translation in 70+ languages. Here's how it works, where it ships, and how to build with it.
H Company's Holo3.1 family brings computer-use agents to local and on-device inference with quantized checkpoints and four model sizes. Here's what shipped and how to deploy it.
A practical 2026 comparison of Kimi K2.6, GPT-5.5, and Claude Opus 4.8 on coding benchmarks, reasoning, pricing, and self-host economics — plus which to pick by use case.
A practical 2026 comparison of faster-whisper, whisper.cpp, and OpenAI's reference Whisper — speed, VRAM, accuracy, and which local speech-to-text runtime to pick for your hardware.
Install and run OpenAI Whisper's largest model locally for private, offline transcription — VRAM requirements, pip and Apple Silicon setup, faster-whisper, and quantization.
A practitioner's roundup of every AI model release that mattered in May 2026 — Anthropic Mythos, Gemini 3.5 Flash, Qwen 3.7 Max, Mistral Medium 3.5, ERNIE 5.1, and Subquadratic's 12M-token SubQ. Benchmarks, pricing, availability, and what to actually use.
Baidu's ERNIE 5.1, released May 8 2026, became the first Chinese LLM in the global Search Arena top 5. Here's what it does, how it compares to DeepSeek V4 and Qwen, and when teams outside China should actually use it.
Anthropic Mythos is the frontier preview model unveiled April 7, 2026: stronger than Opus 4.7 on math and security, withheld from public release, shipped only via Project Glasswing to ~50 defensive-security partners.
Claude Mythos, Opus 4.7, and GPT-5.5 shipped within three weeks of each other in April 2026. We break down which frontier model wins on coding, reasoning, vision, cost, and which one your team should actually pick.
Alibaba's Qwen 3.7 Max launched May 20, 2026 with a 1M-token context, native extended-thinking mode, and benchmark wins on SWE-Pro and Terminal-Bench. Here's how it compares to Claude Opus 4.7, GPT-5.5, Gemini 3.5 Flash and DeepSeek V4, what it costs on DashScope, and when to pick it.
Google dropped Gemini 3.5 Flash and Gemini Spark at I/O 2026. A frontier-grade Flash model that outruns 3.1 Pro, and a persistent personal agent built on top of it. Here's what shipped, what's rumored, and where it fits next to Claude Opus 4.7 and GPT-5.5.
Every major LLM and AI tooling release in May 2026 — Qwen 3.7-Max, DeepSeek V4-Pro permanent pricing, Gemini 3.5 Flash, Composer 2.5, Grok Build, Cherry Studio 1.9.6, Ollama 0.24, and what's still rumored.
The xformers `Could not load library libcuda.so` error almost always traces to a missing symlink, wrong LD_LIBRARY_PATH, or a CUDA/wheel version mismatch. Here is a step-by-step debug guide with the exact commands.
Qwen 3.6 is shipping with open weights today. Qwen 3.7-Max was announced May 20 with previews live but no weights yet. A grounded side-by-side.
MiniMax M3 is not released as of May 2026. Here's what's actually shipping (M2.7), where the 'M3.0 released' claim came from, and how to verify it.
Claude Sonnet 4.8 is not announced as of May 19, 2026. The honest status check: what's shipping, where the rumor came from, and what to run now.
GPT-5.6 (Sol, Terra, Luna) hit general availability on July 9, 2026. Release timeline, the July 30 price cuts, Ultrafast, Cyber, and what to run now.
Gemini 3.5 Flash shipped May 19, 2026; 3.6 and 3.7 Flash followed. Gemini 3.5 Pro never launched and is delayed indefinitely. Full timeline and what to run today.
Is Qwen 3.7 released? As of May 2026 it isn't — no weights, API, or benchmarks. Here's what's real, what's only rumored, and what to run today.
SubQ claims to be the first fully subquadratic LLM with a 12M-token context window. Here's what's verified, what isn't, and why the architecture matters.
Ant Group's inclusionAI shipped Ring-2.6-1T, a trillion-parameter open-weights reasoning MoE. What it is, the vendor benchmarks, how it stacks up against Kimi K2.6 and DeepSeek V4, and whether you can run it.