Software.
Everything I've written about software. Start at the top; the list compounds.
By domain.
software posts.
Showing 21–30 of 71.
Gemini 3.5 Flash: What the 3.1 - 3.5 Jump Changes for Builders
Google released Gemini 3.5 Flash yesterday at I/O. The headline that actually matters for builders: a Flash-tier model that beats the previous-generation Pro across coding and agentic benchmarks while running roughly four times faster than other frontier model
Gemini Omni: Multimodal Generation Crosses a Production Threshold
The release that has the least clear practical implication from I/O is also the most strategically interesting. Gemini Omni is a multimodal generation model that takes image, audio, video, and text as input and outputs video. The output is "grounded in real-wo
Why HTML Beats Markdown for Claude Code Plans and Specs
I have stopped writing markdown plans for Claude Code. Not because markdown stopped working, but because I stopped reading them. Once the model started running long enough to produce thousand-line plans, my honest behaviour was to skim, lose the loop, and shru
Google's Managed Agents API: A Production Agent in One Call
The most consequential developer announcement from I/O isn't a new model. It's a new primitive: the Managed Agents API. One API call spins up a fully provisioned agent — sandboxed Linux environment, tool use, code execution, persistent context — running on Gem
Cursor 3 Builder's Guide: 7 Things That Changed for Production Code (2026)
Cursor 3 is the first version of the product that isn't a VS Code skin. The editor has been rebuilt around agents instead of files, and after six weeks of using it as my daily driver the change is bigger than the marketing makes it sound. It is not "an IDE wit
Cursor Composer 2.5 Builder's Guide: 10× Cheaper Than Opus 4.7 (2026)
Composer 2.5 shipped yesterday. The headline number, accurate as far as I can tell, is that it sits within striking distance of Claude Opus 4.7 and GPT-5.5 on coding benchmarks while costing roughly a tenth as much per task. If that holds up in your workloads,
5 Levels of Using Claude in 2026: From First Chat to Always-On Architect
Most people using Claude are stuck one level below their actual potential. Not because they lack the skill to operate the next surface, but because they cannot picture what the next ceiling looks like, so they keep optimising the one they're already on. This e
Migrating From GPT 5.4 to GPT 5.5: A Practical Migration Playbook
Migrating production LLM features from one model version to the next is mostly mechanical. change a string, ship the build. until it isn't. The places it bites: subtle output differences your prompt-test suite missed, cost shifts you didn't notice, and behavio
ChatGPT 5.5 Multimodal Patterns: Vision, Audio, and Mixed Inputs
Multimodal LLM features have moved from "interesting demo" to "real production capability" over the last two years. With GPT 5.5, vision and audio inputs are reliable enough to ship into customer-facing features for use cases like document analysis, visual sup
ChatGPT 5.5 for Coding Tasks: Where It Wins and Where It Doesn't
Asking "is GPT 5.5 good at coding?" is the wrong question. The right question is: for which coding tasks does it produce reliable, useful output, and when should you reach for a different tool? The answer is more granular than the marketing makes it sound, and