Insights for AI builders
Tutorials, product updates, and ideas to help you build and ship AI applications faster.
Subscribe via RSS
Mistral Large 4 Coding Test: Can "Le Chonk" Finish What It Starts?
Mistral Large 4 (Le Chonk) faced eight agentic coding tasks in Open Code. Here's how it scored, where it failed, and where it impressed.
Step 5 Preview Pricing: API Costs and October 15 Weights Release
Stepfun's Step 5 Preview API pricing per million tokens, cached input discounts, and the planned October 15 open-weight release explained.
Step 5 Preview Tested: Stepfun's MoE Model Scores 83.75% on Kingbench
Stepfun's Step 5 Preview MoE model takes on eight Kingbench coding tasks, from an archery game to local Gemma fine-tuning, scoring 83.75%.
Turnstone: Orchestrating AI Coding Agents Across Local Hardware
Turnstone lets you distribute AI coding agent tasks across DGX Station, GB10 clusters, and RTX Pro 6000 rigs. Here's how it actually works.
What Is an AI Harness? Claude Code and Codex Explained
AI harnesses like Claude Code and Codex control how models act. Learn the five components: context, memory, tools, verification, permissions.
How to Mash Up Two Games With AI Using Universal Moder
A practical look at Universal Moder, the GitHub skill that lets coding agents merge two owned games into one playable mod.
AI Just Published 722 Math Proofs. Who Checks Them?
OpenAI released 722 AI-generated math manuscripts in one month. Here's why verifying them matters more than the results themselves.
Aleph Alpha Kolibri 1: Germany's Open-Weight MoE Reasoning Model
Kolibri 1 is Aleph Alpha's 78B mixture-of-experts model for German and English, with 1M-token context and Apache 2.0 licensing.
Google EmbeddingGemma 2: How One Model Embeds Text, Images, and Audio
Google's EmbeddingGemma 2 maps text, images, video, and audio into one 768-dim vector space under Apache 2.0. Here's how it actually works.
Hark by Figure: Pricing, Free Trial, and What It Actually Does
Figure, the humanoid robot company, launched an AI assistant called Hark at $100/month with a free trial. Here's what's known so far.
Holo4 Benchmarks: How H Company's Agent Model Stacks Up vs Frontier AI
Holo4's OSWorld scores and cost-per-task compared to GPT-5.5 and Claude Opus, plus why the dense model beats the MoE variant.
Is Holo4 Free to Use? License and Commercial Use Explained
Holo4's open weights from H Company are free to download, but licensing and API access affect what you can actually ship with them.
Holo4: The Open-Weight Agent That Clicks, Codes, and Calls Tools
H Company's Holo4 is an open-weight agent model that chooses between GUI clicks, code execution, and MCP tool calls. Here's how it works.
Run Kandinsky 6.0 Locally: RTX 4090 Guide to the Open Video Model
Kandinsky 6.0 is an open-source text-to-video model that runs on consumer GPUs. Here's how to install it locally or use it via Fal.ai.
Kolibri 1 Benchmarks: How It Stacks Up Against GPT-OSS and GLM
Kolibri 1's MoE design and bilingual training compared against GPT-OSS, GLM-4.7 Flash, Nemotron, and Qwen on size and architecture.
Mistral Large 4 (Le Chat): Hands-On Testing of the New Flagship
Mistral Large 4, aka Le Chat, tested on reasoning, vision, code security, and multilingual tasks against rivals like GLM 5.3.
Mistral Large 4 "Le Chonk": Pricing, Specs, and Benchmarks Explained
Mistral Large 4, nicknamed Le Chonk, is a trillion-parameter open-weight model. Here's its pricing, architecture, and how it stacks up on benchmarks.
Mistral Large 4: Pricing, Access, and Open-Weight Release Date
Mistral Large 4 is live in API preview on Mistral Studio now, with open weights promised by month's end. Here's how access works.
OpenAI's 722 Math Proofs: What Its Secret Model Actually Found
OpenAI released 722 math manuscripts from an unreleased model touching the Riemann hypothesis and Navier-Stokes. Here's what it actually shows.
Tencent Prism: Open-Source 2K Video AI Needs 80GB VRAM
Tencent's Prism generates native 2K AI video with audio from a single image, but its 80GB VRAM requirement keeps it out of consumer reach.
How to Run EmbeddingGemma 2 Locally With Sentence Transformers
Step-by-step guide to installing Google's EmbeddingGemma 2 locally, with measured VRAM use and text, image, and Matryoshka embedding tests.
Giving an AI Coding Agent Browser Access: Tiny Fish Setup and Pricing
How Tiny Fish's MCP server adds free web search, page fetch, and paid browser automation to DeepSeek Harness or any coding agent.
How to Build a Claude Agent That Thinks Like a Real Expert
A four-step method for turning a real expert's public writing into a Claude Code wiki and sub-agent that mimics their reasoning, not just their words.
CodeAF Coding Agent: Running It Locally With Ollama, Tested
A hands-on look at CodeAF, the Go-based coding agent harness, tested locally with Ollama models and OpenRouter, including its crew and task-split features.