IMHO highly underestimated episode. With all the hype surrounding RAG and LLMs and hallucinations, this short interview gives a great mental framework. ❤
// next time please use a different camera placement, where the microphone is not in the face of the interviewee. + its a little bit strange to see the reporter on the divided screen all time. usually it is important if his reaction, face expression has some meaning in the interview.
RAG is so over rated... right? 🤔 Why is it given so much attention, I don't get it. Until it can actually answer questions or derive information that isn't explicitly found in the document store it seems kind of weak... Like if you encode Alice in Wonderland , what kind of answer am I going to get if I ask, "What's the symbolic significance of Alice's repeated changes in size throughout the story?" Or if I vectorize and index all the Disney movies and ask, "How do the evolution of the themes of 'family' and 'friendship' reflect the changing societal values and expectations over the years these Disney films were released?" I mean, RAG isn't going to be any help here right?
@@theoreticalorigamiresearch186 A bit of context here might help - I went there to interview Ed Grefenstette and he introduced Patrick during that interview and I then immediately interviewed Patrick - so there was no preparation. I will do a longer form and prepared(!) interview with Patrick again in the near future :)
Great guest! Thanks for highlighting this work! 👏😸
RAG is super interesting with so much potential. Cant believe this videos been here since February.
Must watch for sure
I smiled once when I saw the MLST notification and then a second time within the first 5 seconds! 2 ✌🏾points Tim!!
thanks for giving them som
e love, really interesting startup in terms of hacking their way vs brute forcing
This was infinitely fascinating. I was asking ChatGPT for explanations all throughout.
Thanks 💓
IMHO highly underestimated episode. With all the hype surrounding RAG and LLMs and hallucinations, this short interview gives a great mental framework. ❤
I came here for the doggy boy!
// next time please use a different camera placement, where the microphone is not in the face of the interviewee. + its a little bit strange to see the reporter on the divided screen all time. usually it is important if his reaction, face expression has some meaning in the interview.
RAG is so over rated... right? 🤔 Why is it given so much attention, I don't get it. Until it can actually answer questions or derive information that isn't explicitly found in the document store it seems kind of weak... Like if you encode Alice in Wonderland , what kind of answer am I going to get if I ask, "What's the symbolic significance of Alice's repeated changes in size throughout the story?"
Or if I vectorize and index all the Disney movies and ask, "How do the evolution of the themes of 'family' and 'friendship' reflect the changing societal values and expectations over the years these Disney films were released?"
I mean, RAG isn't going to be any help here right?
Thats a very disrespectful way to talk to your guest. I guess with lot of views comes lot of pride and hubris.
I'm sorry you thought that, do you mind explaining why? Was it the dog? It's their office dog, she's part of the cohere family
@@MachineLearningStreetTalk I don't think you were disrespectful, and the dog did a great job. 👍
Not sure which part is disrespectful. That's a very posh dog for a "Street Talk" show 🐩
@@MachineLearningStreetTalk Pretty sure it's because you got his name wrong.
@@theoreticalorigamiresearch186 A bit of context here might help - I went there to interview Ed Grefenstette and he introduced Patrick during that interview and I then immediately interviewed Patrick - so there was no preparation. I will do a longer form and prepared(!) interview with Patrick again in the near future :)