coder (@sujal_maiti) 's Twitter Profile
coder

@sujal_maiti

Sr Associate @ATT ||ex Intern @WellsFargo | intern @unremot_HQ @zupay_in || SME @ChainCouncil , SDE at GoGame, Research Intern @nokia,Symbiosis,@Chegg

ID: 992968964773998593

calendar_today06-05-2018 03:27:04

7,7K Tweet

600 Followers

779 Following

Manthan Gupta (@manthanguptaa) 's Twitter Profile Photo

Security has completely gone off the rails! And most might not even realize it, because if you look at just the last month, the number of serious incidents across the AI dev ecosystem is honestly insane. Axios, a package with over 100M weekly downloads, was allegedly hijacked

coder (@sujal_maiti) 's Twitter Profile Photo

some people have very strong choices based on prev experience Although I understand to some extend but sticking to strong opinions w/o any rationale is weird unnecessary blocker writing in an abstract way but yeah :⁠-⁠)

coder (@sujal_maiti) 's Twitter Profile Photo

hot take: more evals ≠ better agents what actually works: – eval real prod behaviors – learn from failures (dogfooding + traces) – optimize for correctness → then efficiency evals aren’t metrics, they’re control knobs for agent behavior 👀

coder (@sujal_maiti) 's Twitter Profile Photo

have been building slew of demos for few of the freelancing clients with whom I work using Emergent hot dang, insane results :⁠-⁠)

coder (@sujal_maiti) 's Twitter Profile Photo

it's extremely extremely extremely critical to understand system design now as these agentic ai systems scales, design decision becomes one of the most imp skill

Arpit Bhayani (@arpit_bhayani) 's Twitter Profile Photo

"It depends" is what most senior engineers say when asked almost anything. Yes, it is a real answer, but, according to me, it should be followed by an explanation. Without that, it is just a way to sound 'smart' while saying nothing literally. To be fair, many decisions