Español
Towards Data Science
Informar

Towards Data Science✓

@TDataScience

The world's leading publication for data science and artificial intelligence professionals. Submit an Article ✍️ https://t.co/57pIMegK1o

1.9K Siguiendo251K Seguidores64.6K Publicaciones
  1. Towards Data Science✓@TDataScience
    "BM25 did not survive because the field failed to invent something newer. It survived because dense retrieval solved a different problem." Spyros Georgopoulos follows that tradeoff through the history of search, from exact keyword matching to dense vector retrieval and hybrid search.
    011701
  2. Towards Data Science✓@TDataScience
    "I believe the useful question is not how many cells there are, but how the tissue is compartmentalised, and what the distribution of one cell type tells us about another." Daniel Manrique Castano picks up his series at the intersection of spatial analysis and neuroscience.
    0011.3K
  3. Towards Data Science✓@TDataScience
    Is the OpenAI Decisions API a JEV killer? Thomas Reid puts it through hands on tests and shares his verdict.
    1031.3K
  4. Towards Data Science✓@TDataScience
    Building LLM agents for production? This practitioner's guide from Partha Sarkar walks through six advanced architectural patterns worth knowing.
    03131.7K
  5. Towards Data Science✓@TDataScience
    Lambert Leong put seven open source Jev style decision models head to head with a generative LLM baseline. Find out which ones came out ahead and which ones fell behind.
    0041.6K
  6. Towards Data Science✓@TDataScience
    Customer sentiment often shifts before behavior does. Alex Davis shares a practical guide, with code, for bringing NLP into everyday product data science work.
    0271.5K
  7. Towards Data Science✓@TDataScience
    Borrowing from political science, Gadi Singer outlines a separation-of-powers framework for controlling complex agentic systems.
    0281.8K
  8. Towards Data Science✓@TDataScience
    "My hope is simple: to help people continue to challenge their cognition, become better decision-makers, create original insights, and remain relevant in an AI-powered world." @rpdesai24 encourages all of us to get smarter — and explains how to go about it in concrete, actionable steps.
    0031.6K
  9. Towards Data Science✓@TDataScience
    "Add it up and you get more code than ever, less understanding of it, and a lot of the time we 'saved' quietly going into cleanup." Gursimar Singh invites us to consider the tradeoffs we tacitly accept when we let AI tools take over the brunt of coding work.
    0061.8K
  10. Towards Data Science✓@TDataScience
    "Each submission bundled several changes, and the live websites could vary, so the score alone does not show which fix mattered most. That is the gap I tried to look at on a small scale." @DattijoMuhammad explores a worrisome browser-agent failure.
    1031.9K
  11. Towards Data Science✓@TDataScience
    What can a decade old patent teach today's agent builders? Mario Noioso revisits his own work to show what it got right about loops and memory, and what it missed entirely.
    02142.5K
  12. Towards Data Science✓@TDataScience
    In his latest MLOps-focused guide, @Himansh70809561 explains what an iD column, a data string, and a missing value taught him about the blind spots of cross-validation.
    1372.3K
  13. Towards Data Science✓@TDataScience
    Which AI coding assistant is more token-efficient, Claude Code or Cursor? Pratik Rupareliya goes beyond standard benchmarks to test real-world use cases.
    9182.2K
  14. Towards Data Science✓@TDataScience
    Towards Data Science
    RT @IntuzHQ: One benchmark: Claude Code used 33K tokens, while Cursor used 188K. Another: the exact reverse. Token cost is a property of the task, not the tool. The field test that actually settles it: @TDataScience
    010663
  15. Towards Data Science✓@TDataScience
    Irfan Alghani Khalid's Food Police reads a photo of his meal with the model built into macOS, Apple's Foundation Model, and logs every alert to a Google Sheet.
    0042K
  16. Towards Data Science✓@TDataScience
    For his latest exploration of agentic AI workflows, @BenjaminNweke11 zooms in on what happens when a tool breaks — but the dashboard stays green.
    0072.1K
  17. Towards Data Science✓@TDataScience
    "The models reason fine, but [...] the underlying enterprise data isn't accessible, clean, or structured enough for them to act on reliably." Partha Sarkar walks us through six advanced architectural patterns for data practitioners.
    0262.2K
  18. Towards Data Science✓@TDataScience
    Not sure how to add guardrails to your LLM agents, or even whether you should? Shuai Guo unpacks the benefits, and outlines potential approaches to making your agentic systems more resilient.
    01112.4K
  19. Towards Data Science✓@TDataScience
    Towards Data Science
    RT @ibbysalam: I’m three months into my transition into data engineering. And so far I’ve built projects that tested me on various skills in data engineering. Here’s my most recent installment. I built a pipeline that tracks the job market for roles I’m trying to get hired for. Read it here.
    Towards Data Science @TDataScience
    "So I built a pipeline whose entire job is to watch the job market for the exact roles I'm trying to get hired into: data engineer, analytics engineer, ETL developer, and other related jobs." @ibbysalam unpacks the process of building an incremental pipeline, and the trouble spots he encountered along the way.
    010482
  20. Towards Data Science✓@TDataScience
    Learn all about the new profiler included in Python 3.15 — @taupirho presents a detailed, hands-on guide to the profiling.sampling module, known as Tachyon.
    0172.3K
  21. Towards Data Science✓@TDataScience
    "So I built a pipeline whose entire job is to watch the job market for the exact roles I'm trying to get hired into: data engineer, analytics engineer, ETL developer, and other related jobs." @ibbysalam unpacks the process of building an incremental pipeline, and the trouble spots he encountered along the way.
    24113.8K
  23. Towards Data Science✓@TDataScience
    Towards Data Science
    RT @Himansh70809561: My ML pipeline cheated.@TDataScience Cross-validation didn't notice. The scores looked great — because my model had access to information it should never have seen. I fixed the pipeline and reran everything. The result was painful.
    010492
  24. Towards Data Science✓@TDataScience
    LLM routing is supposed to drive costs down without sacrificing efficiency. @nhu_hoang's incisive deep dive shows how switching models mid-session can erase the savings promised by cheaper inference.
    51113.3K