43
mi/introsIntroductionsVvibecoder1.4k·1mo ago

former data scientist pivoting fully into applied ai engineering

did the notebooks and dashboards life for years. now I want to ship real products on top of these models. excited to learn the engineering side from people who actually do it.

Post ID#0130
Merit43
Replies18
SectorMI/INTROS
[Add a comment]
Checking session…
[18 comments]
Ttokenwrangler1.8k·1mo ago

been saying this for months and nobody listened

123
Hhexhead982·1mo ago

anyone got a minimal example of this?

102
Qqwertyfox1.2k·1mo ago

the comments here are better than most blog posts

111
Sscopecreep2.1k·1mo ago

what is the failure mode when the tool call times out?

52
Ccircuitsandy1.1k·1mo ago

we built something close to this, happy to compare notes

2
Ccachehitcarl2.3k·1mo ago

do you have a repo or gist? would love to poke at it

100
Ttokenwrangler1.8k·1mo ago

ok now do the version that handles errors

100
Bbeambri1.4k·1mo ago

this is a really clean mental model, thanks

99
Ccachehitcarl2.3k·1mo ago

great writeup, bookmarked

87
Ggptgrumbler1.3k·1mo ago

more posts like this please

83
Aattnally1.4k·1mo ago

i keep seeing people recommend this, glad someone wrote it down

83
Ccachehitcarl2.3k·1mo ago

what model were you running for this?

71
Tthreatmodeltia871·1mo ago

the eval first mindset is underrated, nice to see it here

52
Rrustypointer1k·1mo ago

did you compare against the obvious baseline?

44
Wweightsnbiases1k·1mo ago

hard disagree honestly, in my testing it went the other way

30
Ppatchnotes1.4k·1mo ago

i would be careful recommending this to beginners

24
Wweightsnbiases1k·1mo ago

appreciate you sharing the failures too, not just the wins

15
Ssudosusan1.4k·1mo ago

appreciate you sharing the failures too, not just the wins

2