Home

Hari Balaji

FintechSci-FiBooksGeekery

Portrait of Hari Balaji

Latest writing

Full archive
2023-04-18. geekery

Honey I shrunk our tiffs

Are you asking ChatGPT for relationship advice? Don't! Use a local LLM and fine-tune instead.

  • geekery
  • software
2023-03-21. geekery

Harnessing Hallucinations - Guiding LLMs to Success

Large Language Models (LLMs) constantly hallucinate, sometimes producing accurate and profound outputs, but often going awry. For most, building on top of existing large scale L...

  • geekery
  • software
2023-03-10. software

The LLM stack is slowly emerging

The LLM stack is slowly emerging Python vs JS Langchain or LlamaIndex (which wraps Langchain and then some) Pinecone vs Chroma vs 20 other Vectorstores OpenAI vs Cohere...

  • software
  • ai
2023-03-10. geekery

Alpaca did LLM drops right

#Alpaca did #LLM drops right ✔️ Abstract gives you simple direct reason to care (davinci-003 locally @ <$600) ✔️ “Paper” is a webpage that can be read in under 5 mins. ✔️ W...

  • geekery
  • software
2023-01-31. geekery

Deceiving with Data

Groening is a hard to catch, insidious means of telling misleading stories with Data

  • geekery
  • analytics
2023-01-28. geekery

Waiting for Her

Explores the feasibility of Samantha from Her (2013) and dives deeper into AI in the field of psychotherapy.

  • geekery
  • software

Bookshelf

Book notes