Using “prompts” to drive LLMs (Large Language Models)
HBR in 2012 had declared ‘Data Scientist’ as the Sexiest job in 21st century. Looking at the rage of LLM’s that we are seeing these days, one will need to change that proclamation, to say that ‘Prompt Engineer’ is that sexiest job.
Last month itself (January 2023), Anthropic advertised a…
At the time of joining Medium, the sole thought was to publish my content at one place, which otherwise was spread all over, in GitHub repositories, YouTube comments, LinkedIn articles, etc.
Took some time for me to get the structure and the mechanism of this site, but with the help…
Unless you are living under the rock, it would be impossible that you have not heard of ChatGPT. It feels as if it has taken Artificial Intelligence (AI, or even for some, AGI i.e. Artificial General Intelligence) at the Peak on the Gartner Hype Cycle, because anybody-and-everybody is talking about…
Documents are made up of paragraphs, which in-turn are made up of sentences, which in-turn are made up of words. That’s the usual representation of documents.
More abstract way could be that documents are made of themes or concepts or topics, such that a document is, say, 40% politics, 30% sports and 30% entertainment.
Following patent is about representing a contract document by a sequence of clause categories, say [‘preamble’, ‘recitals’, ‘term’,….,’signature’]. Almost like a genome sequence, only difference is instead of letters A, T, C, G, the contract document is made up of sequence of clause categories-symbols.
This terse representation is effective in various downstream machine learning based natural language processing workflows such as document similarity, contract type classification, etc.
Data Science was there for ages but was not as popular as today. Stars aligned due to availability of data, compute power and libraries/tool. catapulting its growth like never before. HBR even called the Data Scientist job as the “The Sexiest Job of the 21st Century”.
With all that jazz, no wonder folks are getting attracted to data science. But what does that entail? Here are my points for Transitioning to Data Science, a Learning Path.
SaaS industry is going leaps-and-bounds with the overall industry growing almost 500% over past seven years. SaaS is nothing but an application that is served from cloud, and users pay per use. Salesforce, Zendesk are some major examples. Micro SaaS is a smaller and a niche application serving a very specific need and clientele. Sketchnote below gives an overview of the landscape.
To make money, you need Specialization, Leverage, Accountability - Specialization: unfair advantage, non-trainable, unique combination. - Leverage: Force multiplier like software which works while u r sleeping. - Accountability: Taking responsibility, Delivering value, being a Brand. - Compounding is core.