Is there a reason not to use built in macOS transcribing? Genuinely curious what the goal is here, though points given for coolness factor.
HN user
dllrr
I've been a fan of Orbstack for make 2 years or so. Worth the cost for me because it's so well integrated and fast and docker command compatible.
I'll give this a try though.
While I like the article there are way too many telltale signs of AI writing. I'm sure the author expresses his direction but I'm just so tired of reading articles where AI has done most of the work. I want to hear from humans, grammar and spelling and punctuation mistakes and all.
The productivity gains are well worth any nits I have about responding to the LLM.
LLM: "I've just refactored your code base. Would you like me to also fully document it?"
op: "you're so needy!!!"
And here I thought engineers were mostly logical and objective. This thread is very entertaining.
I just used Claude to convert my app to a serverless architecture and migrated to Cloudflare and their generous tiers. Not every app fits that model, but it's more than you'd think. Now I only pay when the app is used, not a penny more.
I just tested it with a max subscription. On Ultracode mode, Fable 5 ate up 10% of my weekly allowance in 30 minutes. Granted, won't be using UC mode frequently, but still.
They said they would release it back into subscriptions as capacity allows in the future. If they don't, people are going to point back at it and rake them over the coals.
And why do the numbers sound impressive but the words are verrrry specific (authenticating a new ... what?! What does that even f'ing mean?!)
Hilarious
Cloudflare artifacts??
Guess I've been enjoying it for so long, I feel so stupid. Thanks for this.
For fun and education purposes, learning and satisfaction are understandable.
For work, companies won't support it. Get it done. Fast. That's the new norm.
This video provides a much better walk through of the application.
A data generator and visual data modeler for any database. It's been fun, learned a LOT about generating data in a very specific order to maintain referential integrity, even more about how to determine that order! Generates > 100K rows a second for simple generation, or ~10K rows a second for derived / child rows.
https://app.synthforge.io to login (FREE!) or https://synthforge.io to learn more
Using opus 4.6 in claude code right now. It's taking about 5x longer to think things through, if not more.
Truer words have never gone so hard. Damn this hits.
Same as hombre_fatal - I used to use iStats Menus, but no need any longer. This is great. I'm watching multiple SSDs activity, network activity, cpu, memory, etc.