It's sort of two books combined into one: The first one is the story of OpenAI from the beginning, with all the drama explained with quotes from inside sources. This part was informative and interesting. It includes some details about Elon being convinced that Demis Hassabis is going to create an evil super-intelligence that will destroy humanity, because he once worked on a video game with an evil supervillain. I guess his brain was cooked much earlier than we thought.
The second one is a bunch of SJW hand-wringing about things that are only tangentially related, like indigenous Bolivians being oppressed by Spanish Conquistadors centuries ago. That part I don't care for as much.
I struggle with this a bit because while my network isn’t bad - I really can’t stand social network like threads/X etc - I’m not on any social media bar here and LinkedIn.
Do you think investing in bluesky is worth it? I’m in industry but have a PhD ongoing in TTI models so I should probably get on it :/
I do understand why it’s a product - it feels a bit like what databricks has with model artifacts. Ie having a repo of prompts so you can track performance changes against is good. Especially if say you have users other than engineers touching them (ie product manager wants to AB).
Having said that, I struggled a lot with actually implementing langfuse due to numerous bugs/confusing AI driven documentation. So I’m amazed that it’s being bought to be really frank. I was just on the free version in order to look at it and make a broader recommendation, I wasn’t particularly impressed. Mileage may vary though, perhaps it’s a me issue.
I thought the docs were pretty good just going through them to see what the product was. For me I just don't see the use-case but I'm not well versed in their industry.
I think the docs are great to read, but implementing was a completely different story for me, ie, the Ask AI recommended solution for implementing Claude just didn’t work for me.
They do have GitHub discussions where you can raise things, but I also encountered some issues with installation that just made me want to roll the dice on another provider.
They do have a new release coming in a few weeks so I’ll try it again then for sure.
Edit: I think I’m coming across as negative and do want to recommend that it is worth trying out langfuse for sure if you’re looking at observability!
I’ve been slowing crunching through Math for Deep Learning, so spent a fair amount of time looking at Hessian matrices + second order optimisation. I’ve been slowly reading this book for a year, so stopping to do most of the math by hand each time. One chapter to go!
Then I was sick all last week, so ended up down a rabbit hole about the current card collecting bubble (right word?). Super interesting.
Where do Hessians come into play for neural networks? It seems like they just use auto-diff to compute the Jacobian or the gradient for backpropagation.
The theoretical results sometime look at the second order derivative.
This is fantastic. I think it’s nailed in the substack what was missing from a lot of these LLM driven NPCs that did not feel authentic. I have a couple of follow-up questions on specifics relating to analysis of behaviour with LLMs (in game-dev myself). Would it be possible to speak to you directly on them?
reply