Danny Aziz

Every launches Spiral v3, an AI writing assistant powered by Claude Opus 4 that uses editorial taste and multi-agent systems to help users write authentic short-form content in their own voice.

“Co-author of the article and sole engineer who built Spiral v3 in a few months”

Droid, Factory's agentic coding product, enables developers and non-coders to switch between GPT and Claude mid-task to optimize for each phase of work without switching tools.

“General manager of Spiral and Droid's biggest evangelist at Every who built the newest version of Spiral using Droid's multi-model workflows.”

Spiral, a new AI writing tool, prioritizes thoughtful creation over speed by slowing users down and asking targeted questions to deepen ideas rather than generating surface-level drafts.

“General manager of Spiral, an AI writing tool, discusses philosophy of using AI with intention to avoid creating 'slop'”

Anthropic's new subagents feature enables engineers to parallelize AI-assisted workflows by managing up to 10 specialized agents simultaneously, multiplying developer productivity through compounding improvements.

“Demonstrated the executor/evaluator loop pattern using subagents for Spiral's onboarding screens and UI engineering workflows.”

GPT-5.2 is an incremental upgrade that excels at extended knowledge work tasks (70.9% on GDPVal vs 38.8% for GPT-5.1) but offers minimal improvement for everyday chat, with real gains expected when powering agentic tools.

“Ran GPT-5.2 through 50 user writing requests and found it scored 74 percent on criteria like reader engagement.”

AI coding tools like Cursor and Claude Code are eliminating traditional software engineering work, forcing developers to redefine their professional identity and choose between coasting with AI assistance or using freed-up time to develop new skills.

“Wrote about how AI coding tools like Cursor and Claude Code changed his identity as a software engineer by suddenly doing his technical work.”

Anthropic's Claude agents feature enables AI systems to create other agents independently, representing a shift toward 'compounding engineering' where systems build systems iteratively.

“Worked with Kieran Klaassen to test-drive Claude Code agents and debug AI orchestration.”

Factory's Droid coding agent enables seamless switching between different AI models (Claude, GPT) without context loss, making it superior to individual subscription plans for production engineering workflows.

“Part of the team walking attendees through how to use Factory AI's Droid tool at the Droid Camp event.”

Anthropic's Claude Sonnet 4.5 consolidates writing and editing workflows previously split between ChatGPT and Claude, with the model demonstrating strong performance in both code and prose quality assessment.

“Built Spiral, an AI writing tool informed by editorial tastes that helps users think better and write better, and trains models to produce stellar copy.”

Anthropic's new cloud and mobile version of Claude Code shows promise but is not yet ready for daily use, lacking features like inline code diffs and seamless task transition between devices.

“Has his own Claude Code setup running on a server and uses Codex on the web to handle small bug fixes.”

Three major AI labs released multiple significant models in a single week—Genie 3 (interactive 3D worlds), Claude Opus 4.1 (coding improvements to 74.5% on SWE-bench), and GPT-5—signaling intensifying competition for model dominance.

“Commented on the competitive timing of AI model releases, describing it as 'petty AI wars'.”

DSPy is an automated prompt-optimization framework that has made traditional manual prompt engineering largely obsolete, with the author stopping manual prompt writing in favor of DSPy-optimized prompts.

“Learned DSPy prompt optimization framework from Michael Taylor in a video tutorial.”