Category
Technologies
LLM Articles
Keep up to date with the latest techniques, tools, and research in Large Language Models. Our blog talks about data science, uses, & responsible AI practices.
Other technologies:
Training 2 or more people?Try DataCamp for Business
TypeSafe Jev vs GPT-6 Astra: Decision Model or Frontier Agent?
Jev decides in milliseconds and cannot write a word; GPT-6 Astra finishes whole tasks unattended. Here is which pipeline steps belong to each model, and what they cost.
Tom Farnschläder
September 21, 2026
Bonsai 2 27B: Run a 27B AI Locally on Your Laptop
PrismML's Bonsai 2 27B compresses a 27B multimodal model to 5.9GB while keeping 98.2% of full-precision benchmark performance, and it runs on a laptop.
Matt Crabtree
September 18, 2026
Qwen3.8-Omni-Flash: Alibaba's Omnimodal Agent Model
Alibaba's Qwen3.8-Omni-Flash handles text, image, audio, and video with a 1M-token context window, beating Gemini 3.8 Flash on audio benchmarks.
Matt Crabtree
September 18, 2026
DeepSeek V4.1 Flash vs Gemini 3.8 Flash: Benchmarks, Pricing, and Which to Use
DeepSeek's open-weight V4.1 Flash matches Gemini 3.8 Flash on agentic coding benchmarks at a third of the price. We compare specs, costs, and a hands-on build test.
Tom Farnschläder
September 17, 2026
Jev: TypeSafe's System One Model That Never Hallucinates
TypeSafe's Jev is a new class of AI model, a System One Model, that returns typed decisions with calibrated probabilities instead of text, running 40-200x faster than frontier LLMs.
Matt Crabtree
September 16, 2026
ChatGPT Images 2.5: Features, Sketch, Templates, and API Models
OpenAI's new image model brings sharper details, up to 50% faster generation, and new ChatGPT tools like Sketch and templates, plus two API models.
Matt Crabtree
September 9, 2026
5 GPT-6 Astra Projects to Test Out OpenAI’s New Model
Discover five GPT-6 Astra projects that can help you explore the new features and upgrades of OpenAI’s new model.
Matt Crabtree
September 9, 2026
The Best Free AI Text-to-Video Generators in 2026: Features, Pros, Cons, and Pricing
Discover the best free text-to-video AI generators and their pros and cons. Compare features, pricing, and more.
Brooke Webber
September 7, 2026
GPT-6 Astra vs Claude Fable 5.1: Performance, Pricing, and Which to Use
Two frontier models arrived at exactly the same list price, and OpenAI's own benchmark table and the independent index disagree on which one leads.
Tom Farnschläder
September 5, 2026
GPT-6 Astra: Features, Benchmarks, Pricing, and How to Access It
OpenAI's GPT-6 Astra tops computer use, coding, and math benchmarks. Full breakdown of features, scores vs Claude and Gemini, pricing, and how to access it.
Matt Crabtree
September 3, 2026
Muse Spark 1.3: Meta's Agentic and Coding Model Update
Meta's Muse Spark 1.3 improves agentic workflows and coding, using ~20% fewer tool calls and ~25% fewer tokens than 1.2, with a 1M context window.
Matt Crabtree
September 3, 2026
Gemini 3.8 Flash and 3.8 Flash Cyber: Features, Benchmarks, and Pricing
Google's third Flash release in six weeks pushes coding and agentic reasoning at the same low price as 3.7 Flash, plus a dedicated cybersecurity variant.
Matt Crabtree
September 2, 2026