Tech podcast

 Tech podcast

AI learning

 AI learning resources

RAG pipeline

 RAG pipeline

Computational bio engineering

 compbioeng.biodis.co

"“Data is being created in a lot of different places, and that data has its own gravity: It’s going to cost you money and time to move it,” Tso explains. “That means the end state is a distributed cloud that reaches out to edge devices and servers. You have to bring the cloud to the data, not the data to the cloud.” Cloudian-helps-data-storage-keep-up-with-ai-revolution

Machine Learning in Computational biology

AI engineering book

learn periodic table in 2 days

Engineering performance

Reinforcement Learning

 The Bitter Lesson for AI from 2019

Verification as the key to reasoning LLMs

Dont teach. Incentivize

Assessing the quality of code generated by AI

mlabonne llm-course

Task specification

 Task specification - " writing concrete chunks of code/comments myself and in the right part of the code is a high bandwidth way of communicating "task specification" to the LLM, i.e. it's primarily about task specification bits - it takes too many bits and too much latency to communicate what I want in text, and it's faster to just demonstrate it in the code and in the right place. "

AI cheatsheet

Japanese afshinea/stanford-cme-295

Encryption of data from your prompt to LLM and cloud

From chatgpt: 

User Device

   |

   |  📡 TLS 1.3

   v

API Gateway / CDN

   |

   |  🔒 mTLS (optional)

   v

LLM Frontend (e.g., OpenAI API)

   |

   |  🔐 Internal encrypted service calls (gRPC, mTLS)

   v

LLM Core Services (Tokenizer, Model, Storage, Cache)

   |

   |  💾 At-rest encryption via AES-256

   v

Cloud Storage / Logs / Backups (with KMS/HSM)