10 posts
Seven open decision models produced different results for classification, moderation, and scoring. I measured latency and memory, then published every probability needed to check the results.
#tools · #ai · #rust · #mlx · #benchmarks
TypeSafe's new model answers questions without writing a single word. An open-weight counterpart now does the same on my Mac in 40 milliseconds, and one of my first tests showed where it stops being trustworthy.
#tools · #ai · #rust · #mlx · #coding-agents
I gave sayneat one recording. The next terminal message came back in my own voice, generated locally without Python, a GPU, or an account.
#tools · #text-to-speech · #ai · #rust · #voice-cloning
Sounds and speech bring me back to the right terminal. Tests, diffs, and worktrees keep several coding sessions useful. The limit is no longer typing speed. It is review.
#pi · #coding-agents · #tmux · #tools · #ai
I replaced macOS say with sayneat, a local text-to-speech CLI. Six voices handled the same stubborn build very differently.
#tools · #text-to-speech · #rust · #ai
A 256-line Bash wrapper keeps the best part of macOS say, but replaces its voice with OpenAI speech that sounds startlingly human.
#tools · #text-to-speech · #shell · #ai · #dotfiles
Run git config --global push.autoSetupRemote true once, then a plain git push will create and track a matching remote branch.
A 2009 product idea connecting mite time tracking with Ballpark invoicing.
Adding the current Git branch to Bash PS1 without breaking prompt width calculation.
Introducing mite.cmd, a terminal interface for time tracking with mite.
#ruby · #cli · #tools · #freelancing