The world's leading publication for data science and artificial intelligence professionals. Submit an Article ✍️ https://xitter.cf/t.co/57pIMegK1o
We're Global 🌏
Joined October 2016
- Tweets64.6K
- Following1.9K
- Followers251K
- Likes8K
The challenge with AI is no longer just getting it to do the work; it is finding the time to check the results. Gursimar Singh explains how this shift changes the way we think about assigning tasks to AI agents.
towardsdatascience.com/stop-…
"Ten documents, one count: not one number in any of their gates depends on where the decision threshold sits."
Don't miss Maxim Podstrechnyy helpful deep dive on a common quantization-gate pain point. towardsdatascience.com/the-n…
You'd think that adding an agentic element to RAG would consistently improve results. As @DattijoMuhammad demonstrates, the reality is more complicated than that. towardsdatascience.com/does-…
"If the hint points at a wrong option and the model moves to it, there is a good chance the hint did that."
@mangal_utkarsh digs into the inner workings of LLMs' reasoning process by planting wrong hints and recording the models' responses to them. towardsdatascience.com/same-…
Can a model teach itself new skills without forgetting old ones?
Jonathan Yahav breaks down on-policy self-distillation, the technique behind dozens of papers since January, and explains why it seems to reduce catastrophic forgetting. towardsdatascience.com/could…
Raw Raman spectra are rarely ready for modeling. @NCocaLopez walks us through the full pipeline (cropping, spike removal, baseline correction, normalization), and uses non-negative least squares to track a zeolite phase transformation. towardsdatascience.com/raman…
Towards Data Science retweeted
Big thanks to the @TDataScience team for featuring my new piece in the Editor's Picks. If you’re curious about how skills and MCP reshape trust boundaries in LLMs, this one’s for you.
towardsdatascience.com/skill…
Why does taking your shirt off to celebrate still earn a yellow card when the goal is disallowed?
Irfan Alghani Khalid built a football referee assistant that answers from the text of Law 12, not the model's memory, and shows the paragraph it used.
towardsdatascience.com/ai-as…
"Did someone make a mistake? Is the data broken? Did Python quietly decide to ruin your afternoon? (It does that sometimes; we’ve all been there.)"
Sara A. Metwalli presents a beginner-friendly introduction to Simpson's paradox. towardsdatascience.com/both-…
Is the "always switch" approach always the right one for participants in a Monty Hall-like scenario?
Samit Ganguly explains why the host's position and prior knowledge can change everything. towardsdatascience.com/infer…
LLMs or decision models? Why not both!
Shuai Guo's hands-on guide to hybrid LLM workflows shows how to build browser automation by combining decision models with LLMs. towardsdatascience.com/decis…
We're thrilled to welcome Anand Rawat to TDS — we invite everyone to explore his excellent article on transforming long-running Python simulations into a self-service platform. towardsdatascience.com/how-t…
Don't miss the latest installment in @ibbysalam's data engineering learning journey — this time, walking us through the process of building an incremental pipeline with dbt snapshots. towardsdatascience.com/i-bui…
For an incisive look at the areas where AI models hit a wall, read Lars Benedikt Kaesberg and Jan Philip Wahle's debut TDS article, which focuses on spatial reasoning and the grid puzzles that trip up powerful language and vision models. towardsdatascience.com/spati…
Towards Data Science retweeted
Cheaper LLMs ≠ Lower costs.
Great insights from Nhu Hoang on @TDataScience about the hidden costs of LLM routing.
Optimizing AI isn't just about model pricing—it's about total cost, latency, and quality.
Worth a read 👇
towardsdatascience.com/the-h…
#LLM #AIEngineering
Cheaper LLMs don't always mean lower costs.
While exploring LLM routing, I found that switching models has hidden costs too.
towardsdatascience.com/the-h…
#LLM #GenerativeAI #AIEngineering #LLMRouting #AgenticAI
Towards Data Science retweeted
Okay, finally I can announce it.
So excited to make a comeback for @TDataScience !
So here is the glimpse for what I made,
Towards Data Science retweeted
I wrote an article for @TDataScience, and it ended up as an Editor’s Pick
It’s about grid puzzles people solve easily, but the best AI models still get stuck on, and what this tells us about their spatial reasoning skills. Thanks to @jpwahle for the help!
towardsdatascience.com/spati…
Towards Data Science retweeted
Cheaper LLMs don't always mean lower costs. While exploring LLM routing, I found that switching models has hidden costs too. Check it out at @TDataScience
#LLM #GenerativeAI #AIEngineering #LLMRouting #AgenticAI
Switching to a cheaper model should... lower your overall costs, right?
@nhu_hoang Nhu Hoang explains why that's not always the case, and stresses the importance of verifying the hidden costs of LLM routing. towardsdatascience.com/the-h…
Towards Data Science retweeted
Stacking doesn't automatically beat your best model.
Diverse models: 0.830 vs 0.820 ✅
Correlated tree ensembles: +0.1 at 35x the training cost ❌
Plain voting lost to the best single model both times.
@TDataScience
Full test + notebook:
towardsdatascience.com/does-…
Behind every news story about an AI-related safety failure, we can likely detect a range of technical causes.
Stephanie Kirmer unpacks the processes that can lead to such failures and the steps teams and practitioners can take to mitigate them. towardsdatascience.com/ai-ha…
