It’s 2am. The agent loop just hallucinated my schema for the third time tonight, and the diff looked confident right up until it tried to rename a table that didn’t exist. That’s the annoying part of github copilot vs cursor: both can feel brilliant for 20 minutes, then one tiny context miss turns into a … Read more
On 14 March I gave the same brief to Claude Sonnet 4.6 and GPT-5: write a product launch angle for a boring B2B API, then rewrite it for a newsletter audience. Claude gave me a cleaner first draft in 42 seconds. GPT-5 took 58 seconds and produced the sharper hook, but it needed one extra … Read more
On 14 March I gave the same brief to Claude Sonnet 4.6 and GPT-5, then ran the draft through a Chrome-only Prompt API prototype I’d been poking at for 90 minutes. The result was blunt: the Chrome path was faster to demo, but it locked the workflow to one browser in a way I wouldn’t … Read more
The model everyone is praising is worse at shai-hulud themed malware found in the than people admit, especially when the task stops being generic summarization and starts looking like messy incident triage. I ran a small, boringly practical test to check that claim, and the results were less glamorous than the hype. This wasn’t about … Read more
I wasted three weeks on Cursor before realising it was the wrong tool for the kind of work I was doing. On April 7, 2026, I switched my spec-writing to Claude Projects, kept Cursor for edits, and moved the messy planning into Linear. That was the first week I started saying, out loud, that opus … Read more
Stop using ChatGPT as your only writing tool — here’s what to use instead. I ran 60 prompts across three sessions in March 2026, and the difference wasn’t subtle: one tool cut revision time by 31%, another produced cleaner long-form structure, and a third kept hallucinations under 5% on source-heavy briefs. Table of Contents 1. … Read more
I weighed three Monstera pots over 14 days and the numbers barely moved: 4.8 lb, 4.7 lb, and 4.8 lb. That’s the same kind of stubborn consistency I look for in a model review, and it’s why this claude sonnet 4.6 review is less about hype and more about what it actually gets right. At … Read more
Stop using a moisture meter as your only judge of whether your plant needs water. Mine told me a Monstera deliciosa was “fine” at 18% and then I watched the lower leaves go limp anyway. Honestly, plant care advice gets weirdly religious online, so I tested claude vs chatgpt the way I’d test any tool: … Read more