Blog
Guides, news and ideas for working with AI.
CreativeLab API v2: one endpoint for video, images and music
A walkthrough of the new GPTunneL media API: model parameters in the request body, price before generation, idempotent retries, and what to fix when moving off v1.
Learn more
Vibe coding with Claude Code: a live product in two weeks
Gemini 3.7 Flash: benchmarks, price and the API call
Gemini 4: What We Actually Know About Google's Next Frontier Model
Ultrafast: OpenAI made GPT-5.6 Sol 14× faster
Grok 4.6 via API: benchmarks, pricing and the 200K token cliff
WAN 3.0 — what Alibaba's new video AI model can do
Seedance 2.5 — what ByteDance's new video model can do
What a workflow is, in plain words — and how to build an AI one
AI for making collages: top 10 AI services for photo collages
How to use ChatGPT for free: the complete guide
Making a product advert with a neural network
Claude Fable 5.1: what's new?
Composer 3: Cursor's next big move
DeepSeek V4 GA: the important changes nobody told you about
Flux 3: everything about the new multimodal model
Gemini 3.5 Pro: Google's flagship is almost here
Gemini 3.6 Flash: a faster Gemini for the agentic era
GLM-5.3: Z.ai's next move
GPT-6: what's under the hood? Sorting through the leaks together
Grok 2T: xAI bets on two trillion parameters
MiniMax H3: a new challenger to Seedance
MiniMax M3.1: what might be behind the 2.7T M3 Pro rumor
Qwen 3.8: Alibaba takes aim at the top AI tier
