Claude
claude.ai
Claude
Working in technology means one thing above all else: chasing scale. There is a reason why much of the tech world is obsessed with growth. Free from physical constraints, digital systems can scale to an incomprehensible size. The appeal of conquering the engineering, design and business challenges of mega-scale is strong, the rewards immense. But u
... See moreMost hard problems of scale are solved with boring discipline versus random brilliance.
For the deployment side of things, we found that the performance of our training process was quite slow, especially when it gets into these large language models and when you train from scratch. MosaicML offers what's called programmatic optimization, which is not so much on the hardware side of things, but rather on the algorithmic side. Can you f... See more
CB Insights • 2024 Tech Trends
Dario Amodei: Anthropic CEO on Claude, AGI & the Future of AI & Humanity | Lex Fridman Podcast #452
youtube.com- Multiple indices. Splitting the document corpus up into multiple indices and then routing queries based on some criteria. This means that the search is over a much smaller set of documents rather than the entire dataset. Again, it is not always useful, but it can be helpful for certain datasets. The same approach works with the LLMs themselves.
- Cu
Matt Rickard • Improving RAG: Strategies
Tracing the thoughts of a large language model
anthropic.com