756 karma · joined February 24, 2019
- !w: results from last week only
- !y: results from yesterday and today only
- !io: Assistant, but offline
- !ig: Assistant, but for grammar correction
- !itr: Assistant, but for correcting and organizing transcript text
- !sh: Google shopping tab
At least for the CRUDs that I make, I really don't think I need a better model. I just wanted it to get much cheaper.
I really, really hoped you weren't being serious...
But https://web.archive.org/web/20250624143349/https://www.nytim...
I've been preferring to use Copilot agent mode with Sonnet 4, but it asks you to intervene a lot.
A bit of a counterpoint: I've been programming for 12 years, but only recently started working in webdev. I have a general understanding of cybersecurity, but I never had to actively implement security measures in my code until now—and my boss is always pushing for speed.
AI has been incredible in that regard. I can ask it to review my code for vulnerabilities, explain what they are, and outline the pros and cons of each strategy. In just a month, I've learned a lot about JWT, CSRF, DDoS protection, and more.
In another world, my web apps would be far more vulnerable.
I don't think you are. The problem really is execution. I don’t need anything beyond what AI can already do—I just need an assistant that understands what I want and uses the right tools. I’m baffled that we still can’t get a reliable summary of emails, notifications, or appointments. If you give me the data in text format, I can paste it into ChatGPT/Gemini/Claude and have a much better dialogue than with any current phone assistant. Somehow, trillion-dollar companies still haven’t solved that.