Another great example of how ML can be used to improve computer systems, by learning how the system is actually being used (in this case by predicting VM lifetimes for optimizing their placement). Nice work, Pratik Worah and @martin_maas and coauthors!
RESEARCH
-

SWE-grep: ML-Powered Code Search and Explanation Tool
By
–
SWE-grep is truly some inspired ML from @cognition
. Take a 1M line codebase like React. With multiple fast inference calls on Cerebras, it can fetch & explain relevant code in seconds. Here are a few measurements taken on React, Vercel, PyTorch repos. -
Adding Logan Kilpatrick and Hamel Hussain to List
By
–
adding to this list:
– logan kilpatrick (deepmind)
– hamel hussain (eval king, parlance labs) -
CS Fundamentals, Local LLMs, and Inference Explained
By
–
what do you know? cs fundamentals? running llms locally? inference?
-

Generative AI Transforms Engineering and R&D Innovation
By
–
Generative AI is transforming engineering and R&D by enabling automation, intelligent decision-making, and ethical innovation across domains, driving a new phase of productivity, safety, and creativity for organizations that embrace its potential. @NasscomR via @antgrasso
-

Transformers Learning Multiplication Through Auxiliary Loss
By
–
Why Can't Transformers Learn Multiplication? This paper found that plain training never builds long-range links of multiplications. So by adding a new auxiliary loss that predicts the “running sum”, it enables the model to successfully learn multi-digit multiplication!
-
Claude Multi-Agent Systems: Skills, Code, and Future Insights
By
–
Very interesting convo with @ErikSchluntz (multi-agent research lead) about all things agents:
— Alex Albert (@alexalbert__) 17 octobre 2025
– Why Claude is good at agent tasks
– Evolution from workflows to multi-agents
– Tips for creating Skills
– How code unlocks all other domains
– How to use subagents
– The future of… pic.twitter.com/NshRStZVdsVery interesting convo with @ErikSchluntz (multi-agent research lead) about all things agents:
– Why Claude is good at agent tasks
– Evolution from workflows to multi-agents
– Tips for creating Skills
– How code unlocks all other domains
– How to use subagents
– The future of -

Stanford Paper Makes Prompt Engineering Obsolete Forever
By
–
Stanford just killed Prompt Engineering — and that’s a good thing.
A single paper just changed how we understand alignment, diversity, and creativity in AI forever. — RIP Prompt Engineering A groundbreaking new Stanford paper just made it obsolete — with one simple -
PaddleOCR VL 900M Params Achieves SOTA on OmniDocBench
By
–
Pretty wild what 900M params can do – PaddleOCR VL > SOTA on OmniDocBench v1.0 & v1.5 (text, tables, formulas, charts, reading order)
> Multilingual – 109 languages (Latin, Arabic, Cyrillic, Devanagari, Thai, etc)
> Handles handwriting, historical docs, noisy scans
> Supports -

Bee: Open-Source Multimodal LLM Corpus and Framework
By
–
Bee A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs