Ashwin to start refining the introduction

[ashwinvis]

From #7 and #8

• Fix quote

From #8

• Move some cautionary notes to dropdown, refering to "risks" episode

From #17

• Ensure the mood is not too negative

• in-context learning, attention, maybe Word2Vec, tokenization, embedding space, embedding space, wherever the knowledge is stored

• anatomy of LLM

• schematic of LLM and the above terms

• context window figure

• LLM autonomy -> agents

Links for figures here: #17 (comment) and below

From #20

• first we tell all the beautiful things you can do and then all the bad sides with risks (validity, misconduct, cybersecurity, data privacy etc)

• mention context window size and agents -> open models have short context and then things might not work, but we have new models like Qwen 3.8 27B (add link?) and then local memory becomes a bottleneck. some of these open weights models think a lot -> consume context window fast.