Why I'm Sticking With GPT-5.5 Over Claude
A personal comparison of GPT-5.5, Claude, Codex, and Claude Code based on coding workflow, context handling, readability, limits, and developer experience.
Essays and field notes on AI systems, OCR, LLMs, product work, and software delivery.
Start with the newest pieces, or use tags when you want to follow a specific theme. I keep earlier writing available because it shows how the work and ideas developed over time.
A personal comparison of GPT-5.5, Claude, Codex, and Claude Code based on coding workflow, context handling, readability, limits, and developer experience.
A 2-month YouTube automation experiment covering news scraping, video generation, auto-uploading, niche choice, costs, and watch time.
AI changed my job from writing every line to directing parallel software systems. This is my field report from that shift.
A software engineer journey from vibe coding to compound engineering, and what AI changes about architecture, intent, and code quality.
Field notes from building an iOS app with AI coding tools, covering what worked, what failed, and how to ship faster with quality.
A benchmark of Autify OCR versus Google OCR on rendered mobile UI text, including methodology, accuracy metrics, and failure analysis.
An experiment on compressing multiple LLM tokens into one representation for faster decoding and longer effective context.
Experiments on extending transformer context length, including training observations, tradeoffs, and lessons from long-context tuning.
A short opinion post on GPT-4 expectations, scaling constraints, and likely directions for next-generation language models.
How Autify for Mobile uses machine learning for visual regression testing, visual self-healing, and AI-powered app exploration.
A case study on automated mobile app navigation using behavior cloning and heatmap prediction for tap-location modeling.
A practical guide to applying modern deep learning and pre-trained NLP models in production software and product workflows.