2/ The writing test. Everyone says the slop is gone, so I checked.

Two briefs, a release email and a launch post, to Opus 5, Opus 5.5 and GPT-6 Sol. Three drafts each, 18 pieces. Counted em dashes and 37 stock phrases. - Em dashes: zero in 18. Stock phrases: one "excited to",

Parker RexSep 24

1/ The scoreboard. Artificial Analysis rolls ten evals into one number, and Opus 5.5 leads it.

Opus 5.5 at 57.6, Fable 5.1 at 53.4, Opus 5 at 50.8, GPT-6 Sol at 47.5 - Sol scores level with GPT-5.6 on this index, at half the list price of Opus 5.5 - Running the whole index

Parker RexSep 241

Opus 5.5 came out Tuesday and took the week.

What it means if you pay for Claude: - Your plan goes further. People run it all day and use around 10% of their weekly limit - 40% cheaper than Opus 5 and 30% faster. Claude Code made it the default on Pro and Team - Cursor, Devin

Parker RexSep 248

While testing Opus 5.5, I told him, "Create a simple video explaining the Jev model with real-life examples."

He went and produced the visuals with SVG, prepared the video, even connected to ElevenLabs and produced the sound, and completed this process in 5 minutes. Here is the video:

AI Native GuySep 242