🤖 Transformers - micaleel · Scour

After the illusion: what enterprise AI must become 🛠️Feature Engineering

fastcompany.com·47m

Bruce on AI Engineering 🛠️Feature Engineering

heyuan110.com·32m

Introducing talkie: a 13B vintage language model from 1930 💬Natural Language Processing

simonwillison.net·2d

In new Anthropic Fellows research, we discuss “introspection adapters": a tool that allows language models to self-report behaviors they've learned during train... 🎯Recommender Systems

twitter.macworks.dev

·22h

Google Nested Learning Explained: Hope Architecture, Continual Learning, and the End of Frozen LLMs 🤖Machine Learning

aipapersacademy.com·3d

Sam Altman dropped a subtle hint about GPT-6 'with extra goblins' and it didn’t go unnoticed 🛠️Feature Engineering

·10h

The Sequence AI of the Week #851: DeepSeek-V4 and the Architecture of Million-Token Intelligence 🧠Deep Learning

substackcdn.com·1d·Substack

I’m starting to sound like a nutcase at work because upper management keeps trying to implement AI programs and AI assistants... 🗂️Knowledge Management

tumblr.com·15h

Arm Adds Free Toolkit to Analyze AI Agent Performance 🛠️Feature Engineering

Back to BERT in 2026: ModernGENA as a Strong, Efficient Baseline for DNA Foundation Models 💬Natural Language Processing

biorxiv.org·5d

Using Bag-of-Words With PyCharm 💬Natural Language Processing

blog.jetbrains.com·1d

Evaluating complex-valued transformers based on various architectural parameters for image classification 🧮Vector Databases

sciencedirect.com·2h

granite4.1 📓Note-Taking

ollama.com·15h

Adaptive Thinking: Large Language Models Know When to Think in Latent Space 🤖Machine Learning

machinelearning.apple.com·1d

Associative-State Universal Transformers: Sparse Retrieval Meets Structured Recurrence 🧩Sparse Autoencoders

Who Isn't Using GPT 5.5 🛠️Feature Engineering

Every via kill-the-newsletter.com·2h

Spurious alignment between large language models and brains can emerge from non-robust methods and overlooked confounds 🧩Sparse Autoencoders

Presentation: Agents, Architecture, & Amnesia: Becoming AI-Native Without Losing Our Minds 🛠️Feature Engineering

·1d

AI could help human scientists pick promising research topics 📊Data Science

physicsworld.com·9h·Hacker News

Assessing large language model responses to pediatric depression FAQs: a cross-sectional study on readability, accuracy, and sentiment 📊propensity models

frontiersin.org·18h

Log in to enable infinite scrolling