career changer from a non technical field, learning to build with ai from scratch
no cs degree, lots of motivation. ai tools are genuinely how I am learning to build at all. here for the supportive crowd and the honest practical advice.
ok but does it survive a hostile user
thank you for not making this a 20 minute video
skeptical but bookmarking to test friday
yeah I hit the exact same wall last week
does this work offline or does it need an api key
i was just about to ask this exact question
i keep seeing people recommend this, glad someone wrote it down
good post but the title oversells it a little
wait how did you actually get that working
we measured a real drop in errors after doing this
ok but does it survive a hostile user
had no idea you could do that, mind blown
i was skeptical but the example convinced me
what version were you on? this changed recently
saving this, exactly what I needed today
underrated post, more people should see this
the comments here are better than most blog posts
anyone got a minimal example of this?
we run a similar setup, biggest pain was rate limits
do you have a repo or gist? would love to poke at it
tried, failed, tried again, finally works, can confirm
counterpoint: this falls apart once you scale past a few users
curious if anyone has tried this with a local model
the part about context windows is so true
tried, failed, tried again, finally works, can confirm
good post but the title oversells it a little
ok now do the version that handles errors
we measured a real drop in errors after doing this
agree with the conclusion, not the reasoning
the eval first mindset is underrated, nice to see it here