Per token, GPT didn't get cheaper in 14 months and caching is close to its limit. Per solved task, the newest GPT got 9× cheaper since April. So my $240 of subscriptions have an end date: ChatGPT Pro in about half a year, Claude in about two years. Also, einsager is out: dictation that runs on my Codex login.
My recovered AI history contains 76.85 billion tokens. Most are cached input, which changes what the models cost and how much capability I get for the money.
Every check misses stuff. A bug only reaches production if all of them miss it, which is why I think AI code review needs different models with different prompts.
A transparent, series-aware LoL esports power index built around opponent strength, international results, roster continuity, recent form, and uncertainty.
'move fast and break things' is basically the default now, and AI-coding will crank that up even more. the real fix is boring: code review + managing agents well, so you don't ship the next outage or security mess.
A guide to accessing and analyzing your Spotify listening history data. With a tool that creates visualizations for artist and song statistics over time.
Easily sync TickTick with Reclaim using IFTTT and Todoist for a simple, effective integration. Though limited to hourly syncs, it's a solid workaround for now.