Shreyas Kulkarni retweetledi
Shreyas Kulkarni
1.6K posts

Shreyas Kulkarni
@hello_kshreyas
I build, write and explore around AI, data, and technology. | Writing at: https://t.co/PMltlTJCwv
India Katılım Ağustos 2021
77 Takip Edilen264 Takipçiler
Shreyas Kulkarni retweetledi
Shreyas Kulkarni retweetledi
Shreyas Kulkarni retweetledi

Many successful, talented, and humble people are being portrayed as arrogant because, in the eyes of insecure individuals, self-confidence and arrogance look identical.
True humility has little to do with how you speak or how the media depicts you, and everything to do with the "invisible" efforts you make in private, when no one is watching.
English
Shreyas Kulkarni retweetledi
Shreyas Kulkarni retweetledi
Shreyas Kulkarni retweetledi

Hey @YouTube I would pay an extra $10/month on top of YouTube Premium to disable shorts.
I don't want to see another short ever again. Please let me toggle them off.
English
Shreyas Kulkarni retweetledi
Shreyas Kulkarni retweetledi
Shreyas Kulkarni retweetledi
Shreyas Kulkarni retweetledi
Shreyas Kulkarni retweetledi
Shreyas Kulkarni retweetledi

After debugging a few AI applications, I've learned a few things:
• Long prompts are not free. Models don't treat all tokens equally
• Retrieval is worse when you overstuff context
• Multi-step prompts don't solve polluted context
• Bigger models help, but they don't eliminate hallucinations
To avoid getting your model lost with a ton of context:
1. Keep your context as short as possible
2. Put anything critical at the end
3. Structured context works better than narrative dumps
4. Use tools instead of prompts
5. Use reranking to bring the best chunks, not the most
6. Evaluate your system for this failure mode explicitly
English
Shreyas Kulkarni retweetledi
Shreyas Kulkarni retweetledi
Shreyas Kulkarni retweetledi










