Research library
Software engineering
Practical architecture and development decisions for software that people can use, maintain, and adapt.
72 articles · Page 1 of 6
Google Ships EmbeddingGemma 2: Text, Images, Video and Audio in One Vector Space
EmbeddingGemma 2 embeds text, code, image, video and audio in one 768-d space, ungated under Apache 2.0. Real sizes, self-reported scores, what to test.
Claude Sonnet 5.5: Compare Cost per Finished Task
Sonnet 5.5 keeps Sonnet 5 token prices. Its claimed savings come from using fewer tokens. How to test that claim in your workflow.
Holo4 Combines Computer Use and Tools, with Different Licenses
Holo4 spans GUI, code, MCP and API workflows. Its 27B and 35B-A3B checkpoints have different licenses. What to check before evaluation.
OpenAI DevDay 2026: Always-On Dots, GPT-6.1 Sol and Uneven Availability
OpenAI DevDay 2026 announced dots, GPT-6.1 Sol, Ultrafast, Agents API computer use and plugin extensions. What is live now, what it costs and what to test.
Perceptron Mk1.5 Adds Video Tracking for Embodied Agents
Perceptron Mk1.5 adds audio and video tracking. A September 28 assessment of its hosted API, context budget and integration constraints.
Claude Opus 5.5 Cuts Costs and Changes Conversation Handling
Anthropic's Opus 5.5 release lowers token prices. Its preserved-thinking rules also make conversation history a migration concern for custom agents.
GPT-6 Sol and Luna Bring Lower Prices to Agent Work
OpenAI releases GPT-6 Sol and Luna with lower prices and a shared million-token context window. Compare costs, caching and migration constraints.
Bonsai 2 Makes a 27B Model Smaller. The Runtime Still Matters.
Bonsai 2 compresses a Qwen3.8-derived model into a 5.95 GB download. What the custom runtime and separate vision files mean for local use.
Grok 4.7: Check the Whole Agent Bill Before Switching
Grok 4.7 brings a 500K context window and configurable reasoning. What its API pricing, Fast availability and response behavior mean for migration.
Qwen's New Multimodal APIs Serve Different Jobs
Qwen's September releases cover translation, duplex voice and multimodal interaction. Choose an endpoint around the workflow, not the family name.
OpenAI's Agents API Makes the Codex Harness a Managed Service
OpenAI's Agents API enters public beta with managed sessions and sandbox options. What it runs, what it costs, and where application responsibility stays.
GPT-Live-1 Comes to the API: Voice and Reasoning Get Separate Jobs
GPT-Live-1 brings full-duplex voice to the API. How delegation works, what the per-minute price includes, and what to test before switching.