AI MODELS
133 items
132 posts, 1 guide
Qwen3.8-27B is a 27B dense Apache-2.0 model that beats Opus 4.6 Max on SWE-bench Pro (61.7 vs 53.4). Benchmarks, hardware, cost and when to run it.
Grok 4.6 release guide: xAI's agent-focused update matches GPT-5.6 Sol on the AA index at the same $2/$6 pricing, and runs in Cursor and OpenCode.
LFM2.5-VL-3B is a 3B open-weights vision model from Liquid AI that reads screens, grounds objects and calls tools on a laptop. What shipped and how to run it.
Cactus open-sourced Needle 2, a 45M-parameter agentic LLM in a single 14MB binary that runs a full tool-calling session in 28MB of RAM. 500 tok/s on a Raspberry Pi 5, ESP32-S3 class parts, Apache 2.0. Here is what the benchmarks actually show.
Encrypted chain-of-thought from Anthropic, OpenAI and Google APIs can be replayed into weaker models and read verbatim. How the attack works and what leaked.
Muse Glimmer 30B is Meta's Apache 2.0 open-weight multimodal agent model that runs in 24GB. Benchmarks, hardware reality and what the numbers actually say.
Grok Imagine Image 2.0 is xAI's typography-aware image model, ranked second on text-to-image and editing leaderboards and callable via Vercel's AI Gateway.
WeatherNext Cyclones, DeepMind's open-source tropical cyclone model, adds a day of forecast lead time. What the Nature paper shows and how to run the weights.
Meta Muse Code is a terminal coding agent co-trained with Muse Spark 1.2. How the harness works and what the $0.10/$0.20 contributor tier asks in return.
LFM2.5-2.6B is an open-weight on-device agent model from Liquid AI that runs in under 2.5 GB. How it was trained, what the benchmarks say and how to run it.
Qwen 3.8 Max is a 2.4T-parameter MoE with 95B active, a 1M context window and $2/$6 per million tokens on QwenCloud, with open weights promised next week.
Gemini 2.5 Pro and Gemini 3 Flash are deprecated in GitHub Copilot. What GitHub suggests instead, the October follow-up deprecations, and how to migrate.
AI session portability: sealed reasoning, opaque compaction and hidden subagent messages are replacing portable transcripts. Five tests and seven rules for it.
Claude Haiku 5.5 and GPT-6 Luna both list at $0.10/$0.50 per MTok. The price tie breaks at Haiku's 100K cliff, and Anthropic's benchmarks favor Haiku. Checked Oct 8, 2026.
Claude Mythos Preview explained: Anthropic's gated frontier model, who got access through Project Glasswing, what it found, and where the model line went next.
DeepSeek V4 Flash 0731 was re-post-trained for agent work. Its benchmark numbers, native Responses API and Codex support, and how to wire it up today.
DeepSeek V4 Flash 0731 is the official V4 Flash API release, re-post-trained to beat V4-Pro-Preview on agent benchmarks. How to run it in OpenCode today.
Inkling-Small is a 12B-active, Apache 2.0 open-weights MoE that beats the 975B Inkling on agentic coding and tool use at a quarter of the size.

Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.