Case in point was trying to optimise a SQL query. It gave several good ideas to optimise it. Put in the suggested optimised query in another chat and it "optimised" it again. You can repeat this process many times and after a point the optimisation don't make sense.
Any pointers to good resources (papers/blogs) on Agentic AI? Basically looking for in depth understanding of how the recent state of the art systems work.
#lazyTwitter
Has anyone found a way to keep up with latest ML talks on Youtube? There are a lot of interesting talks being put on by big names, but there are not very discoverable.
e.g. how could I have found @srush_nlp's o1 talk earlier?
https://t.co/A1VnULDtZz
I stopped doing CV research because I saw the impact my work was having. I loved the work but the military applications and privacy concerns eventually became impossible to ignore.
https://t.co/DMa6evaQZr
Can I just say I loooove Suno. Some of my favorites:
Dog dog dog dog dog dog dog dog woof woof
https://t.co/3yWAqFGDe3
Chemical elements
https://t.co/p7EEc4iYgd
train_gpt2.c header (who did this lol)
https://t.co/6gz25sxiKA
Suno tutorial (in Suno!):
https://t.co/vN5lPa55Tg
Many others. So good. Anyone else favorites?
I see a lots of requests asking for slides and recordings after a talk. Wonder if actually someone reads them or it it just one more item on the todo list.
What is the most accurate free-to-use LLM today? I tried a simple question with few free LLMs (Claude, ChatGPT, PaLM, Bard) and only Bard got it right consistently.
The simple question was "Should you use a or an with the word "high"?"