Thoughts

Loved the friendship between Grace and Rocky in Project Hail Mary.

Two scientists from two different planets, different civilisations - sent on the same mission to save their planet.

The most interesting part was how Grace figured out a way to communicate with Rocky. Started with the universal language: math. He had rocky spell out then numbers in his voice and then built a speech-to-text / text-to-speech interface with around 250 words vocabulary. He added words to the vocab as they went on.

Loved how Rocky suggested to sacrifice half his fuel and delay going to his planet Erid by 6 years..only so he could send Grace back to Earth. He even risked his own life to save Grace when they came back from Tau seti.

One of the best movies of all time, IMO.

My VPS has 4G memory.

No need to run everything on it.

Make use of Github Actions to run things on batched mode instead.

Just tried that for getting every indonesian street name from Overture Maps.

Batch normalization (Ioffe & Szegedy, 2015) was justified as reducing “internal covariate shift.” Santurkar et al. at MIT (2018) tested this directly and found BN doesn’t reduce covariate shift. In some cases it increases it. The real reason it works: it smooths the loss landscape, making gradients more predictable so you can use higher learning rates. One of deep learning’s most used techniques, adopted for years on an incorrect theory.

Sending anything to my agent files it to Google Drive automatically. Screenshot, PDF, link. Right folder, date-prefixed filename, done.

Sent a screenshot of a paragraph with no attribution. The agent searched the text, found the original article and author. Reverse lookup from a photo.

Dropped a long article I’d been putting off. It split it into 14 themed sections and scheduled a daily email, one per day.

All the popular tools (svg-term-cli, termtosvg, MrMarble/termsvg) convert asciinema recordings to SVG. You have to actually run the commands first. There is no tool that takes a static config and renders a fake terminal session as SVG, which is what you actually want for README demos: clean, controlled output without recording your real shell.

Haiku with skills matches Opus without them. SkillsBench shows skill engineering beats model size.