1. X
  2. Daily Dose of Data Science
Log inSign up
Daily Dose of Data Science
2,681 posts
Daily Dose of Data Science profile banner
user avatar

Daily Dose of Data Science

@DailyDoseOfDS_
Delivering daily insights in DS, ML, RAGs, Agents & AI Engineering. Trusted by over 100k+ readers!
Join for free →
join.dailydoseofds.com
Joined May 2022
2
Following
50.6K
Followers
RepliesRepliesMediaMedia

Log in or sign up for X

See what’s happening and join the conversation

Continue with phone
or
Log in with username or email
Terms·Privacy·Cookies·Accessibility·Ads Info·© 2026 X Corp.
  • Pinned
    user avatar
    Daily Dose of Data Science
    @DailyDoseOfDS_
    Sep 23, 2024
    Get a FREE Data Science E-book (530+ page), featuring over 150 essential lessons in data science and machine learning. Download link in profile.
    Image
    GIF
  • user avatar
    Daily Dose of Data Science
    @DailyDoseOfDS_
    1h
    LLM inference speed with vs. without KV caching: (learn how and why it works below)
    Image
    00:00
    user avatar
    Avi Chawla
    @_avichawla
    1h
    Article cover image
    Article
    KV, Prefix, Prompt and Semantic Caching in LLMs, clearly explained
    Everything you need to understand where your input tokens are being recomputed and what to do about it. It covers the four cache layers from first principles, their trade-offs, what happens when they...
  • user avatar
    Daily Dose of Data Science
    @DailyDoseOfDS_
    Aug 26
    8 RAG architectures for AI Engineers, visually explained:
    Image
  • user avatar
    Daily Dose of Data Science
    @DailyDoseOfDS_
    Aug 25
    CPU vs GPU vs TPU vs NPU vs LPU, explained visually: 5 hardware architectures power AI today. Each one makes a fundamentally different tradeoff between flexibility, parallelism, and memory access. > CPU It is built for general-purpose computing. A few powerful cores handle
    Image
    GIF
    user avatar
    Akshay 🚀
    @akshay_pachaar
    Jul 7
    Article cover image
    Article
    Your KV Caching Is Broken
    A practitioner's guide to KV cache management. How a modern caching architecture cuts input token costs by 90% and speeds up LLM inference by up to 14x. Researchers at Stanford studied how AI agents...
  • user avatar
    Daily Dose of Data Science
    @DailyDoseOfDS_
    Aug 24
    We built our own coding harness, just like Claude Code. (100% open-source) A harness is the code wrapped around an LLM. The model only decides the next step, and the harness handles everything else, planning, tools, memory, and safety. In simple words model acts as the brain
    Image
    GIF
    user avatar
    Akshay 🚀
    @akshay_pachaar
    Jul 15
    Article cover image
    Article
    Let's build Claude Code's harness (step-by-step)
    We will cover everything that goes into building a coding harness, the agent loop, planning, subagents, sandboxing, memory, and checkpointing, built step by step. If you've ever tried building your...
Advertisement
Advertisement