aidevblogs
⌘
K
Blogs
Videos
Tweets
All
LLMs
Computer Vision
MLOps
Agents
Data Engineering
Research
Safety
langchain-classic==1.0.1
LangChain Releases
·
github.com
·
2 days ago
·
LLMs
Google's year in review: 8 areas with research breakthroughs in 2025
Google AI Blog
·
blog.google
·
3 days ago
·
LLMs
langchain-core==0.3.81
LangChain Releases
·
github.com
·
3 days ago
·
LLMs
langchain-core==1.2.5
LangChain Releases
·
github.com
·
3 days ago
·
LLMs
v0.13.0
vLLM Releases
·
github.com
·
4 days ago
·
LLMs
One in a million: celebrating the customers shaping AI’s future
OpenAI Blog
·
openai.com
·
4 days ago
·
LLMs
Continuously hardening ChatGPT Atlas against prompt injection
OpenAI Blog
·
openai.com
·
4 days ago
·
LLMs
The Shape of AI: Jaggedness, Bottlenecks and Salients
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
5 days ago
·
LLMs
v0.13.5
Ollama Releases
·
github.com
·
6 days ago
·
LLMs
2025 LLM Year in Review
Andrej Karpathy
·
karpathy.bearblog.dev
·
6 days ago
·
LLMs
v0.14.0rc0
vLLM Releases
·
github.com
·
7 days ago
·
LLMs
langchain-core==1.2.3
LangChain Releases
·
github.com
·
7 days ago
·
LLMs
Chemical hygiene
Andrej Karpathy
·
karpathy.bearblog.dev
·
7 days ago
·
LLMs
langchain-openai==1.1.6
LangChain Releases
·
github.com
·
7 days ago
·
LLMs
You can now verify Google AI-generated videos in the Gemini app.
Google AI Blog
·
blog.google
·
8 days ago
·
LLMs
v0.13.5-rc1
Ollama Releases
·
github.com
·
8 days ago
·
LLMs
2025 Interconnects year in review
Interconnects (Nathan Lambert)
·
interconnects.ai
·
8 days ago
·
LLMs
Evaluating chain-of-thought monitorability
OpenAI Blog
·
openai.com
·
8 days ago
·
LLMs
AI literacy resources for teens and parents
OpenAI Blog
·
openai.com
·
8 days ago
·
LLMs
Updating our Model Spec with teen protections
OpenAI Blog
·
openai.com
·
8 days ago
·
LLMs
v0.13.0rc4: [v1] Add PrefixLM support to TritonAttention backend (#30386)
vLLM Releases
·
github.com
·
8 days ago
·
LLMs
Addendum to GPT-5.2 System Card: GPT-5.2-Codex
OpenAI Blog
·
openai.com
·
8 days ago
·
LLMs
Introducing GPT-5.2-Codex
OpenAI Blog
·
openai.com
·
8 days ago
·
LLMs
Watch a podcast discussion about Gemini 3 and the future of Search.
Google AI Blog
·
blog.google
·
8 days ago
·
LLMs
Introducing GPT-5.2-Codex
OpenAI Blog
·
openai.com
·
8 days ago
·
LLMs
v0.13.5-rc0: GGML update to ec98e2002 (#13451)
Ollama Releases
·
github.com
·
8 days ago
·
LLMs
langchain-openai==1.1.5
LangChain Releases
·
github.com
·
8 days ago
·
LLMs
Gemini 3 Flash: frontier intelligence built for speed
Google AI Blog
·
blog.google
·
9 days ago
·
LLMs
v0.13.0rc3: [XPU] fix broken fp8 online quantization for XPU platform (#30831)
vLLM Releases
·
github.com
·
9 days ago
·
LLMs
v0.13.0rc2: [ROCm] [Bugfix] Fix torch sdpa hallucination (#30789)
vLLM Releases
·
github.com
·
9 days ago
·
LLMs
Developers can now submit apps to ChatGPT
OpenAI Blog
·
openai.com
·
9 days ago
·
LLMs
langchain-tests==1.1.1
LangChain Releases
·
github.com
·
9 days ago
·
LLMs
langchain-core==1.2.2
LangChain Releases
·
github.com
·
9 days ago
·
LLMs
langchain-openai==1.1.4
LangChain Releases
·
github.com
·
9 days ago
·
LLMs
v0.13.4
Ollama Releases
·
github.com
·
9 days ago
·
LLMs
Measuring AI’s capability to accelerate biological research
OpenAI Blog
·
openai.com
·
10 days ago
·
LLMs
v0.13.4-rc2
Ollama Releases
·
github.com
·
10 days ago
·
LLMs
The new ChatGPT Images is here
OpenAI Blog
·
openai.com
·
10 days ago
·
LLMs
Olmo 3 and the Open LLM Renaissance
Cameron Wolfe
·
cameronrwolfe.substack.com
·
11 days ago
·
LLMs
2025 Open Models Year in Review
Interconnects (Nathan Lambert)
·
interconnects.ai
·
11 days ago
·
LLMs
2025 Year in Review
Eugene Yan
·
eugeneyan.com
·
12 days ago
·
LLMs
v0.13.4-rc1
Ollama Releases
·
github.com
·
13 days ago
·
LLMs
v0.13.4-rc0
Ollama Releases
·
github.com
·
13 days ago
·
LLMs
Bringing state-of-the-art Gemini translation capabilities to Google Translate
Google AI Blog
·
blog.google
·
14 days ago
·
LLMs
Transformers v5.0.0rc0
Transformers Releases
·
github.com
·
14 days ago
·
LLMs
v0.13.3
Ollama Releases
·
github.com
·
14 days ago
·
LLMs
How We Used Codex to Ship Sora for Android in 28 Days
OpenAI Blog
·
openai.com
·
14 days ago
·
LLMs
BBVA and OpenAI collaborate to transform global banking
OpenAI Blog
·
openai.com
·
14 days ago
·
LLMs
Gradient Canvas: Celebrating over a decade of artistic collaborations with AI
Google AI Blog
·
blog.google
·
14 days ago
·
LLMs
v5.0.0rc1
Transformers Releases
·
github.com
·
15 days ago
·
LLMs
Advancing science and math with GPT-5.2
OpenAI Blog
·
openai.com
·
15 days ago
·
LLMs
Increasing revenue 300% by bringing AI to SMBs
OpenAI Blog
·
openai.com
·
15 days ago
·
LLMs
Update to GPT-5 System Card: GPT-5.2
OpenAI Blog
·
openai.com
·
15 days ago
·
LLMs
v0.13.3-rc1: feat: llama.cpp bump (17f7f4) for SSM performance improvements (#13408)
Ollama Releases
·
github.com
·
15 days ago
·
LLMs
New Talk: Building Olmo 3 Think
Interconnects (Nathan Lambert)
·
interconnects.ai
·
15 days ago
·
LLMs
These developers are changing lives with Gemma 3n
Google AI Blog
·
blog.google
·
16 days ago
·
LLMs
Why AGI Will Not Happen
Tim Dettmers
·
timdettmers.com
·
16 days ago
·
LLMs
Auto-grading decade-old Hacker News discussions with hindsight
Andrej Karpathy
·
karpathy.bearblog.dev
·
16 days ago
·
LLMs
v0.13.0rc1
vLLM Releases
·
github.com
·
16 days ago
·
LLMs
v0.13.3-rc0
Ollama Releases
·
github.com
·
17 days ago
·
LLMs
Transforming Nordic classrooms through responsible AI partnerships
Google AI Blog
·
blog.google
·
18 days ago
·
LLMs
v0.12.0
vLLM Releases
·
github.com
·
20 days ago
·
LLMs
The latest AI news we announced in November
Google AI Blog
·
blog.google
·
20 days ago
·
LLMs
v0.14.10
LlamaIndex Releases
·
github.com
·
21 days ago
·
LLMs
From DeepSeek V3 to V3.2: Architecture, Sparse Attention, and RL Updates
Sebastian Raschka
·
magazine.sebastianraschka.com
·
23 days ago
·
LLMs
v0.14.9
LlamaIndex Releases
·
github.com
·
23 days ago
·
LLMs
The space of minds
Andrej Karpathy
·
karpathy.bearblog.dev
·
26 days ago
·
LLMs
[Subscribers only] Dev Writers Retreat 2025: WRITING FOR HUMANS — 10 Fellowship spots left!
Latent Space
·
latent.space
·
28 days ago
·
LLMs
Patch release v4.57.3
Transformers Releases
·
github.com
·
about 1 month ago
·
LLMs
Patch Release v4.57.2
Transformers Releases
·
github.com
·
about 1 month ago
·
LLMs
Group Relative Policy Optimization (GRPO)
Cameron Wolfe
·
cameronrwolfe.substack.com
·
about 1 month ago
·
LLMs
Latest open artifacts (#16): Who's building models in the U.S., China's model release playbook, and a resurgence of truly open models
Interconnects (Nathan Lambert)
·
interconnects.ai
·
about 1 month ago
·
LLMs
Product Evals in Three Simple Steps
Eugene Yan
·
eugeneyan.com
·
about 1 month ago
·
LLMs
Olmo 3: America’s truly open reasoning models
Interconnects (Nathan Lambert)
·
interconnects.ai
·
about 1 month ago
·
LLMs
v0.11.2
vLLM Releases
·
github.com
·
about 1 month ago
·
LLMs
v0.11.1
vLLM Releases
·
github.com
·
about 1 month ago
·
LLMs
Three Years from GPT-3 to Gemini 3
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
about 1 month ago
·
LLMs
The Agent Labs Thesis
Latent Space
·
latent.space
·
about 1 month ago
·
LLMs
Verifiability
Andrej Karpathy
·
karpathy.bearblog.dev
·
about 1 month ago
·
LLMs
Why AI writing is mid
Interconnects (Nathan Lambert)
·
interconnects.ai
·
about 1 month ago
·
LLMs
v0.11.1rc7
vLLM Releases
·
github.com
·
about 1 month ago
·
LLMs
Interview: Ant Group's open model ambitions
Interconnects (Nathan Lambert)
·
interconnects.ai
·
about 1 month ago
·
LLMs
Giving your AI a Job Interview
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
about 1 month ago
·
LLMs
v0.14.8
LlamaIndex Releases
·
github.com
·
about 2 months ago
·
LLMs
5 Thoughts on Kimi K2 Thinking
Interconnects (Nathan Lambert)
·
interconnects.ai
·
about 2 months ago
·
LLMs
Beyond Standard LLMs
Sebastian Raschka
·
magazine.sebastianraschka.com
·
about 2 months ago
·
LLMs
RL without TD learning
Berkeley AI Research (BAIR)
·
bair.berkeley.edu
·
about 2 months ago
·
LLMs
v0.14.7
LlamaIndex Releases
·
github.com
·
about 2 months ago
·
LLMs
PPO for LLMs: A Guide for Normal People
Cameron Wolfe
·
cameronrwolfe.substack.com
·
about 2 months ago
·
LLMs
v0.14.6
LlamaIndex Releases
·
github.com
·
2 months ago
·
LLMs
Burning out
Interconnects (Nathan Lambert)
·
interconnects.ai
·
2 months ago
·
LLMs
An Opinionated Guide to Using AI Right Now
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
2 months ago
·
LLMs
Advice for New Principal Tech ICs (i.e., Notes to Myself)
Eugene Yan
·
eugeneyan.com
·
2 months ago
·
LLMs
Latest open artifacts (#15): It’s Qwen's world and we get to live in it, on CAISI's report, & GPT-OSS update
Interconnects (Nathan Lambert)
·
interconnects.ai
·
2 months ago
·
LLMs
The State of Open Models
Interconnects (Nathan Lambert)
·
interconnects.ai
·
2 months ago
·
LLMs
v0.14.5
LlamaIndex Releases
·
github.com
·
2 months ago
·
LLMs
Patch release v4.57.1
Transformers Releases
·
github.com
·
2 months ago
·
LLMs
Thoughts on The Curve
Interconnects (Nathan Lambert)
·
interconnects.ai
·
3 months ago
·
LLMs
Understanding the 4 Main Approaches to LLM Evaluation (From Scratch)
Sebastian Raschka
·
magazine.sebastianraschka.com
·
3 months ago
·
LLMs
v0.14.4
LlamaIndex Releases
·
github.com
·
3 months ago
·
LLMs
v4.57.0: Qwen3-Next, Vault Gemma, Qwen3 VL, LongCat Flash, Flex OLMO, LFM2 VL, BLT, Qwen3 OMNI MoE, Parakeet, EdgeTAM, OLMO3
Transformers Releases
·
github.com
·
3 months ago
·
LLMs
Taste is your moat — with Dylan Field, Figma
Latent Space
·
latent.space
·
3 months ago
·
LLMs
Animals vs Ghosts
Andrej Karpathy
·
karpathy.bearblog.dev
·
3 months ago
·
LLMs
ChatGPT: The Agentic App
Interconnects (Nathan Lambert)
·
interconnects.ai
·
3 months ago
·
LLMs
REINFORCE: Easy Online RL for LLMs
Cameron Wolfe
·
cameronrwolfe.substack.com
·
3 months ago
·
LLMs
v0.14.3
LlamaIndex Releases
·
github.com
·
3 months ago
·
LLMs
Thinking, Searching, and Acting
Interconnects (Nathan Lambert)
·
interconnects.ai
·
3 months ago
·
LLMs
Coding as the epicenter of AI progress and the path to general agents
Interconnects (Nathan Lambert)
·
interconnects.ai
·
3 months ago
·
LLMs
Patch release v4.56.2
Transformers Releases
·
github.com
·
3 months ago
·
LLMs
v0.14.2
LlamaIndex Releases
·
github.com
·
3 months ago
·
LLMs
How GPT5 + Codex took over Agentic Coding — ft. Greg Brockman, OpenAI
Latent Space
·
latent.space
·
3 months ago
·
LLMs
v0.14.1
LlamaIndex Releases
·
github.com
·
3 months ago
·
LLMs
Training an LLM-RecSys Hybrid for Steerable Recs with Semantic IDs
Eugene Yan
·
eugeneyan.com
·
3 months ago
·
LLMs
Vault-Gemma (based on v4.56.1)
Transformers Releases
·
github.com
·
3 months ago
·
LLMs
On Working with Wizards
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
4 months ago
·
LLMs
On China's open source AI trajectory
Interconnects (Nathan Lambert)
·
interconnects.ai
·
4 months ago
·
LLMs
Huawei Ascend Production Ramp: Die Banks, TSMC Continued Production, HBM is The Bottleneck
SemiAnalysis
·
semianalysis.com
·
4 months ago
·
LLMs
Online versus Offline RL for LLMs
Cameron Wolfe
·
cameronrwolfe.substack.com
·
4 months ago
·
LLMs
Understanding and Implementing Qwen3 From Scratch
Sebastian Raschka
·
magazine.sebastianraschka.com
·
4 months ago
·
LLMs
A Technical History of Generative Media — with Gorkem and Batuhan from Fal.ai
Latent Space
·
latent.space
·
4 months ago
·
LLMs
Patch release v4.56.1
Transformers Releases
·
github.com
·
4 months ago
·
LLMs
Amazon’s AI Resurgence: AWS & Anthropic’s Multi-Gigawatt Trainium Expansion
SemiAnalysis
·
semianalysis.com
·
4 months ago
·
LLMs
What exactly does word2vec learn?
Berkeley AI Research (BAIR)
·
bair.berkeley.edu
·
4 months ago
·
LLMs
Mass Intelligence
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
4 months ago
·
LLMs
The Illustrated GPT-OSS
Language Models Newsletter
·
newsletter.languagemodels.co
·
4 months ago
·
LLMs
GPT-oss from the Ground Up
Cameron Wolfe
·
cameronrwolfe.substack.com
·
4 months ago
·
LLMs
GPT-5 Set the Stage for Ad Monetization and the SuperApp
SemiAnalysis
·
semianalysis.com
·
5 months ago
·
LLMs
Scaling the Memory Wall: The Rise and Roadmap of HBM
SemiAnalysis
·
semianalysis.com
·
5 months ago
·
LLMs
Can coding agents self-improve?
Latent Space
·
latent.space
·
5 months ago
·
LLMs
From GPT-2 to gpt-oss: Analyzing the Architectural Advances
Sebastian Raschka
·
magazine.sebastianraschka.com
·
5 months ago
·
LLMs
GPT-5's Vision Checkup: a frontier VLM, but not a new SOTA
Latent Space
·
latent.space
·
5 months ago
·
LLMs
GPT-5's Router: how it works and why Frontier Labs are now targeting the Pareto Frontier
Latent Space
·
latent.space
·
5 months ago
·
LLMs
GPT-5 Hands-On: Welcome to the Stone Age
Latent Space
·
latent.space
·
5 months ago
·
LLMs
GPT-5: It Just Does Stuff
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
5 months ago
·
LLMs
The Bitter Lesson versus The Garbage Can
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
5 months ago
·
LLMs
Direct Preference Optimization (DPO)
Cameron Wolfe
·
cameronrwolfe.substack.com
·
5 months ago
·
LLMs
The Big LLM Architecture Comparison
Sebastian Raschka
·
magazine.sebastianraschka.com
·
5 months ago
·
LLMs
The Tiny Teams Playbook
Latent Space
·
latent.space
·
5 months ago
·
LLMs
The Hyperstitions of Moloch
Latent Space
·
latent.space
·
6 months ago
·
LLMs
Against "Brain Damage"
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
6 months ago
·
LLMs
LLM Research Papers: The 2025 List (January to June)
Sebastian Raschka
·
magazine.sebastianraschka.com
·
6 months ago
·
LLMs
Reward Models
Cameron Wolfe
·
cameronrwolfe.substack.com
·
6 months ago
·
LLMs
Using AI Right Now: A Quick Guide
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
6 months ago
·
LLMs
Andrej Karpathy on Software 3.0: Software in the Age of AI (UPDATED with Full Transcript)
Latent Space
·
latent.space
·
6 months ago
·
LLMs
Understanding and Coding the KV Cache in LLMs from Scratch
Sebastian Raschka
·
magazine.sebastianraschka.com
·
6 months ago
·
LLMs
The Shape of Compute — with Chris Lattner for Modular
Latent Space
·
latent.space
·
7 months ago
·
LLMs
AI Engineering Goes Mainstream
Latent Space
·
latent.space
·
7 months ago
·
LLMs
AI Agents from First Principles
Cameron Wolfe
·
cameronrwolfe.substack.com
·
7 months ago
·
LLMs
AI Engineer 2025 - Improving RecSys & Search with LLM techniques
Eugene Yan
·
eugeneyan.com
·
7 months ago
·
LLMs
The recent history of AI in 32 otters
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
7 months ago
·
LLMs
Making AI Work: Leadership, Lab, and Crowd
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
7 months ago
·
LLMs
A Guide for Debugging LLM Training Data
Cameron Wolfe
·
cameronrwolfe.substack.com
·
7 months ago
·
LLMs
Exceptional Leadership: Some Qualities, Behaviors, and Styles
Eugene Yan
·
eugeneyan.com
·
7 months ago
·
LLMs
Coding LLMs from the Ground Up: A Complete Course
Sebastian Raschka
·
magazine.sebastianraschka.com
·
8 months ago
·
LLMs
Personality and Persuasion
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
8 months ago
·
LLMs
Llama 4: The Challenges of Creating a Frontier-Level LLM
Cameron Wolfe
·
cameronrwolfe.substack.com
·
8 months ago
·
LLMs
Vibe coding MenuGen
Andrej Karpathy
·
karpathy.bearblog.dev
·
8 months ago
·
LLMs
On Jagged AGI: o3, Gemini 2.5, and everything after
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
8 months ago
·
LLMs
An LLM-as-Judge Won't Save The Product—Fixing Your Process Will
Eugene Yan
·
eugeneyan.com
·
8 months ago
·
LLMs
The State of Reinforcement Learning for LLM Reasoning
Sebastian Raschka
·
magazine.sebastianraschka.com
·
8 months ago
·
LLMs
Defending against Prompt Injection with Structured Queries (StruQ) and Preference Optimization (SecAlign)
Berkeley AI Research (BAIR)
·
bair.berkeley.edu
·
9 months ago
·
LLMs
Repurposing Protein Folding Models for Generation with Latent Diffusion
Berkeley AI Research (BAIR)
·
bair.berkeley.edu
·
9 months ago
·
LLMs
Power to the people: How LLMs flip the script on technology diffusion
Andrej Karpathy
·
karpathy.bearblog.dev
·
9 months ago
·
LLMs
Vision Large Language Models (vLLMs)
Cameron Wolfe
·
cameronrwolfe.substack.com
·
9 months ago
·
LLMs
No elephants: Breakthroughs in image generation
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
9 months ago
·
LLMs
Frequently Asked Questions about My Writing Process
Eugene Yan
·
eugeneyan.com
·
9 months ago
·
LLMs
First Look at Reasoning From Scratch: Chapter 1
Sebastian Raschka
·
magazine.sebastianraschka.com
·
9 months ago
·
LLMs
The Cybernetic Teammate
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
9 months ago
·
LLMs
The append-and-review note
Andrej Karpathy
·
karpathy.bearblog.dev
·
9 months ago
·
LLMs
NVIDIA GTC 2025 - Building LLM-Powered Applications
Eugene Yan
·
eugeneyan.com
·
9 months ago
·
LLMs
Improving Recommendation Systems & Search in the Age of LLMs
Eugene Yan
·
eugeneyan.com
·
10 months ago
·
LLMs
Speaking things into existence
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
10 months ago
·
LLMs
nanoMoE: Mixture-of-Experts (MoE) LLMs from Scratch in PyTorch
Cameron Wolfe
·
cameronrwolfe.substack.com
·
10 months ago
·
LLMs
The State of LLM Reasoning Model Inference
Sebastian Raschka
·
magazine.sebastianraschka.com
·
10 months ago
·
LLMs
A new generation of AIs: Claude 3.7 and Grok 3
One Useful Thing (Ethan Mollick)
·
oneusefulthing.org
·
10 months ago
·
LLMs
Demystifying Reasoning Models
Cameron Wolfe
·
cameronrwolfe.substack.com
·
10 months ago
·
LLMs
How Transformer LLMs Work [Free Course]
Language Models Newsletter
·
newsletter.languagemodels.co
·
11 months ago
·
LLMs
Understanding Reasoning LLMs
Sebastian Raschka
·
magazine.sebastianraschka.com
·
11 months ago
·
LLMs
The Illustrated DeepSeek-R1
Language Models Newsletter
·
newsletter.languagemodels.co
·
11 months ago
·
LLMs
Mixture-of-Experts (MoE) LLMs
Cameron Wolfe
·
cameronrwolfe.substack.com
·
11 months ago
·
LLMs
Launching Version 14.2 of Wolfram Language & Mathematica: Big Data Meets Computation & AI
Stephen Wolfram
·
writings.stephenwolfram.com
·
11 months ago
·
LLMs
SWE-Bench authors reflect on the state of LLM agents at Neurips 2024
Language Models Newsletter
·
newsletter.languagemodels.co
·
12 months ago
·
LLMs
Scaling Laws for LLMs: From GPT-3 to o3
Cameron Wolfe
·
cameronrwolfe.substack.com
·
12 months ago
·
LLMs
2024 Year in Review
Eugene Yan
·
eugeneyan.com
·
about 1 year ago
·
LLMs
Useful to the Point of Being Revolutionary: Introducing Wolfram Notebook Assistant
Stephen Wolfram
·
writings.stephenwolfram.com
·
about 1 year ago
·
LLMs
LLM Research Papers: The 2024 List
Sebastian Raschka
·
magazine.sebastianraschka.com
·
about 1 year ago
·
LLMs
Finetuning LLM Judges for Evaluation
Cameron Wolfe
·
cameronrwolfe.substack.com
·
about 1 year ago
·
LLMs
Seemingly Paradoxical Rules of Writing
Eugene Yan
·
eugeneyan.com
·
about 1 year ago
·
LLMs
My Minimal MacBook Pro Setup Guide
Eugene Yan
·
eugeneyan.com
·
about 1 year ago
·
LLMs
Virtual Personas for Language Models via an Anthology of Backstories
Berkeley AI Research (BAIR)
·
bair.berkeley.edu
·
about 1 year ago
·
LLMs
Automatic Prompt Optimization
Cameron Wolfe
·
cameronrwolfe.substack.com
·
about 1 year ago
·
LLMs
Understanding Multimodal LLMs
Sebastian Raschka
·
magazine.sebastianraschka.com
·
about 1 year ago
·
LLMs
39 Lessons on Building ML Systems, Scaling, Execution, and More
Eugene Yan
·
eugeneyan.com
·
about 1 year ago
·
LLMs
AlignEval: Building an App to Make Evals Easy, Fun, and Automated
Eugene Yan
·
eugeneyan.com
·
about 1 year ago
·
LLMs
Our book, Hands-On Large Language Models, Is Now Out!
Language Models Newsletter
·
newsletter.languagemodels.co
·
about 1 year ago
·
LLMs
Weights & Biases LLM-Evaluator Hackathon - Hackathon Judge
Eugene Yan
·
eugeneyan.com
·
over 1 year ago
·
LLMs
Building A GPT-Style LLM Classifier From Scratch
Sebastian Raschka
·
magazine.sebastianraschka.com
·
over 1 year ago
·
LLMs
Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination
Berkeley AI Research (BAIR)
·
bair.berkeley.edu
·
over 1 year ago
·
LLMs
Model Merging: A Survey
Cameron Wolfe
·
cameronrwolfe.substack.com
·
over 1 year ago
·
LLMs
Building LLMs from the Ground Up: A 3-hour Coding Workshop
Sebastian Raschka
·
magazine.sebastianraschka.com
·
over 1 year ago
·
LLMs
How to Evaluate Jailbreak Methods: A Case Study with the StrongREJECT Benchmark
Berkeley AI Research (BAIR)
·
bair.berkeley.edu
·
over 1 year ago
·
LLMs
New LLM Pre-training and Post-training Paradigms
Sebastian Raschka
·
magazine.sebastianraschka.com
·
over 1 year ago
·
LLMs
Using LLMs for Evaluation
Cameron Wolfe
·
cameronrwolfe.substack.com
·
over 1 year ago
·
LLMs
Are We Ready for Multi-Image Reasoning? Launching VHs: The Visual Haystacks Benchmark!
Berkeley AI Research (BAIR)
·
bair.berkeley.edu
·
over 1 year ago
·
LLMs
LLM Tokenizers, Semantic Search Course, And book update #2
Language Models Newsletter
·
newsletter.languagemodels.co
·
about 2 years ago
·
LLMs
We're Writing a Book! "Hands-On Large Language Models"
Language Models Newsletter
·
newsletter.languagemodels.co
·
over 2 years ago
·
LLMs
LLM University, Generative AI, AI Product Moats
Language Models Newsletter
·
newsletter.languagemodels.co
·
over 2 years ago
·
LLMs
What a Time for Language Models
Language Models Newsletter
·
newsletter.languagemodels.co
·
over 2 years ago
·
LLMs
Coming soon
Language Models Newsletter
·
newsletter.languagemodels.co
·
almost 3 years ago
·
LLMs
Which GPU(s) to Get for Deep Learning: My Experience and Advice for Using GPUs in Deep Learning
Tim Dettmers
·
timdettmers.com
·
almost 3 years ago
·
LLMs
LLM.int8() and Emergent Features
Tim Dettmers
·
timdettmers.com
·
over 3 years ago
·
LLMs
How to Choose Your Grad School
Tim Dettmers
·
timdettmers.com
·
almost 4 years ago
·
LLMs
On Creativity in Academia
Tim Dettmers
·
timdettmers.com
·
over 6 years ago
·
LLMs
A Full Hardware Guide to Deep Learning
Tim Dettmers
·
timdettmers.com
·
about 7 years ago
·
LLMs
Machine Learning PhD Applications — Everything You Need to Know
Tim Dettmers
·
timdettmers.com
·
about 7 years ago
·
LLMs
TPUs vs GPUs for Transformers (BERT)
Tim Dettmers
·
timdettmers.com
·
about 7 years ago
·
LLMs
Deep Learning Hardware Limbo
Tim Dettmers
·
timdettmers.com
·
about 8 years ago
·
LLMs
Understanding LSTM Networks
Chris Olah
·
colah.github.io
·
about 5 hours ago
·
LLMs
Neural Networks, Types, and Functional Programming
Chris Olah
·
colah.github.io
·
about 5 hours ago
·
LLMs
A new way to extract detailed transcripts from Claude Code
Simon Willison
·
simonwillison.net
·
about 6 hours ago
·
LLMs
LWiAI Podcast #229 - Gemini 3 Flash, ChatGPT Apps, Nemotron 3
Last Week in AI
·
lastweekin.ai
·
about 8 hours ago
·
LLMs
Last Week in AI #330 - Groq->Nvidia , ChatGPT Apps, US AI Genesis Mission
Last Week in AI
·
lastweekin.ai
·
about 21 hours ago
·
LLMs
uv-init-demos
Simon Willison
·
simonwillison.net
·
1 day ago
·
LLMs
Quoting Salvatore Sanfilippo
Simon Willison
·
simonwillison.net
·
2 days ago
·
LLMs
MicroQuickJS
Simon Willison
·
simonwillison.net
·
2 days ago
·
LLMs
AprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems
Hugging Face Blog
·
huggingface.co
·
3 days ago
·
LLMs
Cooking with Claude
Simon Willison
·
simonwillison.net
·
3 days ago
·
LLMs
Using Claude in Chrome to navigate out the Cloudflare dashboard
Simon Willison
·
simonwillison.net
·
4 days ago
·
LLMs
Import AI 438: Silent sirens, flashing for us all
Import AI
·
importai.substack.com
·
4 days ago
·
LLMs
Quoting Shriram Krishnamurthi
Simon Willison
·
simonwillison.net
·
5 days ago
·
LLMs
Quoting Andrej Karpathy
Simon Willison
·
simonwillison.net
·
6 days ago
·
LLMs
Sam Rose explains how LLMs work with a visual essay
Simon Willison
·
simonwillison.net
·
6 days ago
·
LLMs
Introducing GPT-5.2-Codex
Simon Willison
·
simonwillison.net
·
7 days ago
·
LLMs
Agent Skills
Simon Willison
·
simonwillison.net
·
7 days ago
·
LLMs
swift-justhtml
Simon Willison
·
simonwillison.net
·
7 days ago
·
LLMs
Your job is to deliver code you have proven to work
Simon Willison
·
simonwillison.net
·
8 days ago
·
LLMs
Inside PostHog: How SSRF, a ClickHouse SQL Escaping 0day, and Default PostgreSQL Credentials Formed an RCE Chain
Simon Willison
·
simonwillison.net
·
8 days ago
·
LLMs
Tokenization in Transformers v5: Simpler, Clearer, and More Modular
Hugging Face Blog
·
huggingface.co
·
8 days ago
·
LLMs
AoAH Day 15: Porting a complete HTML5 parser and browser test suite
Simon Willison
·
simonwillison.net
·
8 days ago
·
LLMs
Gemini 3 Flash
Simon Willison
·
simonwillison.net
·
8 days ago
·
LLMs
LWiAI Podcast #228 - GPT 5.2, Scaling Agents, Weird Generalization
Last Week in AI
·
lastweekin.ai
·
8 days ago
·
LLMs
The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator
Hugging Face Blog
·
huggingface.co
·
9 days ago
·
LLMs
firefox parser/html/java/README.txt
Simon Willison
·
simonwillison.net
·
9 days ago
·
LLMs
The new ChatGPT Images is here
Simon Willison
·
simonwillison.net
·
9 days ago
·
LLMs
s3-credentials 0.17
Simon Willison
·
simonwillison.net
·
9 days ago
·
LLMs
Last Week in AI #329 - GPT 5.2, GenAI.mil, Disney in Sora
Last Week in AI
·
lastweekin.ai
·
10 days ago
·
LLMs
New in llama.cpp: Model Management
Hugging Face Blog
·
huggingface.co
·
15 days ago
·
LLMs
Codex is Open Sourcing AI models
Hugging Face Blog
·
huggingface.co
·
15 days ago
·
LLMs
LWiAI Podcast #227 - Jeremie is back! DeepSeek 3.2, TPUs, Nested Learning
Last Week in AI
·
lastweekin.ai
·
17 days ago
·
LLMs
Import AI 437: Co-improving AI; RL dreams; AI labels might be annoying
Import AI
·
importai.substack.com
·
18 days ago
·
LLMs
Last Week in AI #328 - DeepSeek 3.2, Mistral 3, Trainium3, Runway Gen-4.5
Last Week in AI
·
lastweekin.ai
·
18 days ago
·
LLMs
Introducing swift-huggingface: The Complete Swift Client for Hugging Face
Hugging Face Blog
·
huggingface.co
·
21 days ago
·
LLMs
We Got Claude to Fine-Tune an Open Source LLM
Hugging Face Blog
·
huggingface.co
·
22 days ago
·
LLMs
Transformers v5: Simple model definitions powering the AI ecosystem
Hugging Face Blog
·
huggingface.co
·
25 days ago
·
LLMs
LWiAI Podcast #226 - Gemini 3, Claude Opus 4.5, Nano Banana Pro, LeJEPA
Last Week in AI
·
lastweekin.ai
·
26 days ago
·
LLMs
Taming LLMs with NeMo Guardrails
MLOps Community
·
mlops.community
·
30 days ago
·
LLMs
Last Week in AI #327 - Gemini 3, Opus 4.5, Nano Banana Pro, GPT-5.1-Codex-Max
Last Week in AI
·
lastweekin.ai
·
about 1 month ago
·
LLMs
Continuous batching from first principles
Hugging Face Blog
·
huggingface.co
·
about 1 month ago
·
LLMs
Diffusers welcomes FLUX-2
Hugging Face Blog
·
huggingface.co
·
about 1 month ago
·
LLMs
LWiAI Podcast #225 - GPT 5.1, Kimi K2 Thinking, Remote Labor Index
Last Week in AI
·
lastweekin.ai
·
about 1 month ago
·
LLMs
Open ASR Leaderboard: Trends and Insights with New Multilingual & Long-Form Tracks
Hugging Face Blog
·
huggingface.co
·
about 1 month ago
·
LLMs
20x Faster TRL Fine-tuning with RapidFire AI
Hugging Face Blog
·
huggingface.co
·
about 1 month ago
·
LLMs
Introducing AnyLanguageModel: One API for Local and Remote LLMs on Apple Platforms
Hugging Face Blog
·
huggingface.co
·
about 1 month ago
·
LLMs
Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Models
Hugging Face Blog
·
huggingface.co
·
about 1 month ago
·
LLMs
Easily Build and Share ROCm Kernels with Hugging Face
Hugging Face Blog
·
huggingface.co
·
about 1 month ago
·
LLMs
Authentic Imperfection
Alex Irpan
·
alexirpan.com
·
about 1 month ago
·
LLMs
Join the AMD Open Robotics Hackathon
Hugging Face Blog
·
huggingface.co
·
about 1 month ago
·
LLMs
Import AI 434: Pragmatic AI personhood; SPACE COMPUTERS; and global government or human extinction;
Import AI
·
importai.substack.com
·
about 2 months ago
·
LLMs
Last Week in AI #326 - Qualcomm AI Chips, MiniMax M2, Kimi K2 Thinking
Last Week in AI
·
lastweekin.ai
·
about 2 months ago
·
LLMs
Last Week in AI #325 - OpenAI is for-profit, ChatGPT Atlas, Copilot Mico
Last Week in AI
·
lastweekin.ai
·
about 2 months ago
·
LLMs
Pretraining: Breaking Down the Modern LLM Training Pipeline
MLOps Community
·
mlops.community
·
about 2 months ago
·
LLMs
Import AI 433: AI auditors; robot dreams; and software for helping an AI run a lab
Import AI
·
importai.substack.com
·
about 2 months ago
·
LLMs
LWiAI Podcast #223 - Haiku 4.5, OpenAI DevDay, SB 243
Last Week in AI
·
lastweekin.ai
·
2 months ago
·
LLMs
Import AI 432: AI malware; frankencomputing; and Poolside's big cluster
Import AI
·
importai.substack.com
·
2 months ago
·
LLMs
Last Week in AI #324: OpenAI Deals and DevDay, Haiku 4.5, Veo 3.1
Last Week in AI
·
lastweekin.ai
·
2 months ago
·
LLMs
Import AI 431: Technological Optimism and Appropriate Fear
Import AI
·
importai.substack.com
·
2 months ago
·
LLMs
LWiAI Podcast #222 - Sora 2, Sonnet 4.5, Vibes, Thinking Machines
Last Week in AI
·
lastweekin.ai
·
3 months ago
·
LLMs
Last Week in AI #323 - Sonnet 4.5, Sora 2, Vibes, SB 53
Last Week in AI
·
lastweekin.ai
·
3 months ago
·
LLMs
LWiAI Podcast #221 - OpenAI Codex, Gemini in Chrome, K2-Think, SB 53
Last Week in AI
·
lastweekin.ai
·
3 months ago
·
LLMs
Last Week in AI #322 - Robotaxi progress, OpenAI Business, Gemini in Chrome
Last Week in AI
·
lastweekin.ai
·
3 months ago
·
LLMs
Sometimes you want to skip that CGI Status header
Rachel by the Bay
·
rachelbythebay.com
·
3 months ago
·
LLMs
A guide to understanding AI as normal technology
AI Snake Oil
·
normaltech.ai
·
4 months ago
·
LLMs
LWiAI Podcast #220 - Gemini 2.5 Flash Image, Claude for Chrome
Last Week in AI
·
lastweekin.ai
·
4 months ago
·
LLMs
Making the most of a dumb fax switcher box in the old days
Rachel by the Bay
·
rachelbythebay.com
·
4 months ago
·
LLMs
Import AI 426: Playable world models; circuit design AI; and ivory smuggling analysis
Import AI
·
importai.substack.com
·
4 months ago
·
LLMs
Ten Years Later
Alex Irpan
·
alexirpan.com
·
4 months ago
·
LLMs
Import AI 424: Facebook improves ads with RL; LLM and human brain similarities; and mental health and chatbots
Import AI
·
importai.substack.com
·
5 months ago
·
LLMs
Import AI 423: Multilingual CLIP; anti-drone tracking; and Huawei kernel design
Import AI
·
importai.substack.com
·
5 months ago
·
LLMs
Import AI 422: LLM bias; China cares about the same safety risks as us; AI persuasion
Import AI
·
importai.substack.com
·
5 months ago
·
LLMs
Brony Musicians Seize The Means of Production: My Eyewitness Account to BABSCon 2025
Alex Irpan
·
alexirpan.com
·
5 months ago
·
LLMs
Import AI 421: Kimi 2 - a great Chinese open weight model; giving AI systems rights and what it means; and how to pause AI progress
Import AI
·
importai.substack.com
·
5 months ago
·
LLMs
Could AI slow science?
AI Snake Oil
·
normaltech.ai
·
5 months ago
·
LLMs
Life lessons from reinforcement learning
Jason Wei
·
jasonwei.net
·
5 months ago
·
LLMs
Asymmetry of verification and verifier’s rule
Jason Wei
·
jasonwei.net
·
5 months ago
·
LLMs
Import AI 420: Prisoner Dilemma AI; FrontierMath Tier 4; and how to regulate AI companies
Import AI
·
importai.substack.com
·
5 months ago
·
LLMs
Documenting what you're willing to support (and not)
Rachel by the Bay
·
rachelbythebay.com
·
6 months ago
·
LLMs
Import AI 419: Amazon's millionth robot; CrowdTrack; and infinite games
Import AI
·
importai.substack.com
·
6 months ago
·
LLMs
Calculating rollovers
Rachel by the Bay
·
rachelbythebay.com
·
6 months ago
·
LLMs
AGI is not a milestone
AI Snake Oil
·
normaltech.ai
·
8 months ago
·
LLMs
[AINews] Grok 3 & 3-mini now API Available
AI News (Buttondown)
·
buttondown.com
·
8 months ago
·
LLMs
[AINews] Gemini 2.5 Flash completes the total domination of the Pareto Frontier
AI News (Buttondown)
·
buttondown.com
·
8 months ago
·
LLMs
[AINews] OpenAI o3, o4-mini, and Codex CLI
AI News (Buttondown)
·
buttondown.com
·
8 months ago
·
LLMs
[AINews] SOTA Video Gen: Veo 2 and Kling 2 are GA for developers
AI News (Buttondown)
·
buttondown.com
·
8 months ago
·
LLMs
[AINews] GPT 4.1: The New OpenAI Workhorse
AI News (Buttondown)
·
buttondown.com
·
9 months ago
·
LLMs
[AINews] not much happened today
AI News (Buttondown)
·
buttondown.com
·
9 months ago
·
LLMs
[AINews] not much happened today
AI News (Buttondown)
·
buttondown.com
·
9 months ago
·
LLMs
[AINews] Google's Agent2Agent Protocol (A2A)
AI News (Buttondown)
·
buttondown.com
·
9 months ago
·
LLMs
Problems with the heap
Rachel by the Bay
·
rachelbythebay.com
·
9 months ago
·
LLMs
Moving To Substack
Jay Alammar
·
jalammar.github.io
·
9 months ago
·
LLMs
You might want to stop running atop
Rachel by the Bay
·
rachelbythebay.com
·
9 months ago
·
LLMs
A Visual Guide to LLM Agents
Maarten Grootendorst
·
newsletter.maartengrootendorst.com
·
9 months ago
·
LLMs
More thoughts on the 1670 modem's weird noises
Rachel by the Bay
·
rachelbythebay.com
·
10 months ago
·
LLMs
Two modems, a length of line cord, and no battery
Rachel by the Bay
·
rachelbythebay.com
·
10 months ago
·
LLMs
A Visual Guide to Reasoning LLMs
Maarten Grootendorst
·
newsletter.maartengrootendorst.com
·
11 months ago
·
LLMs
MIT Mystery Hunt 2025
Alex Irpan
·
alexirpan.com
·
11 months ago
·
LLMs
Common pitfalls when building generative AI applications
Chip Huyen
·
huyenchip.com
·
11 months ago
·
LLMs
Using AI to Get the Neopets Destruct-o-Match Avatar
Alex Irpan
·
alexirpan.com
·
12 months ago
·
LLMs
Agents
Chip Huyen
·
huyenchip.com
·
12 months ago
·
LLMs
Is AI progress slowing down?
AI Snake Oil
·
normaltech.ai
·
about 1 year ago
·
LLMs
We Looked at 78 Election Deepfakes. Political Misinformation is not an AI Problem.
AI Snake Oil
·
normaltech.ai
·
about 1 year ago
·
LLMs
Late Takes on OpenAI o1
Alex Irpan
·
alexirpan.com
·
about 1 year ago
·
LLMs
Reward Hacking in Reinforcement Learning
Lilian Weng
·
lilianweng.github.io
·
about 1 year ago
·
LLMs
Does the UK’s liver transplant matching algorithm systematically exclude younger patients?
AI Snake Oil
·
normaltech.ai
·
about 1 year ago
·
LLMs
A Visual Guide to Mixture of Experts (MoE)
Maarten Grootendorst
·
newsletter.maartengrootendorst.com
·
about 1 year ago
·
LLMs
FAQ about the book and our writing process
AI Snake Oil
·
normaltech.ai
·
about 1 year ago
·
LLMs
Can AI automate computational reproducibility?
AI Snake Oil
·
normaltech.ai
·
over 1 year ago
·
LLMs
Start reading the AI Snake Oil book online
AI Snake Oil
·
normaltech.ai
·
over 1 year ago
·
LLMs
What's Missing From LLM Chatbots: A Sense of Purpose
The Gradient
·
thegradient.pub
·
over 1 year ago
·
LLMs
AI companies are pivoting from creating gods to building products. Good.
AI Snake Oil
·
normaltech.ai
·
over 1 year ago
·
LLMs
Nine Years Later
Alex Irpan
·
alexirpan.com
·
over 1 year ago
·
LLMs
AI existential risk probabilities are too unreliable to inform policy
AI Snake Oil
·
normaltech.ai
·
over 1 year ago
·
LLMs
Building A Generative AI Platform
Chip Huyen
·
huyenchip.com
·
over 1 year ago
·
LLMs
A Visual Guide to Quantization
Maarten Grootendorst
·
newsletter.maartengrootendorst.com
·
over 1 year ago
·
LLMs
The Tragedies of Reality Are Coming for You
Alex Irpan
·
alexirpan.com
·
over 1 year ago
·
LLMs
Extrinsic Hallucinations in LLMs
Lilian Weng
·
lilianweng.github.io
·
over 1 year ago
·
LLMs
AI scaling myths
AI Snake Oil
·
normaltech.ai
·
over 1 year ago
·
LLMs
Successful language model evals
Jason Wei
·
jasonwei.net
·
over 1 year ago
·
LLMs
Financial Market Applications of LLMs
The Gradient
·
thegradient.pub
·
over 1 year ago
·
LLMs
AI Snake Oil is now available to preorder
AI Snake Oil
·
normaltech.ai
·
over 1 year ago
·
LLMs
Tech policy is only frustrating 90% of the time
AI Snake Oil
·
normaltech.ai
·
over 1 year ago
·
LLMs
Mamba Explained
The Gradient
·
thegradient.pub
·
over 1 year ago
·
LLMs
What I learned from looking at 900 most popular open source AI tools
Chip Huyen
·
huyenchip.com
·
almost 2 years ago
·
LLMs
Car-GPT: Could LLMs finally make self-driving cars happen?
The Gradient
·
thegradient.pub
·
almost 2 years ago
·
LLMs
Predictive Human Preference: From Model Ranking to Model Routing
Chip Huyen
·
huyenchip.com
·
almost 2 years ago
·
LLMs
A Visual Guide to Mamba and State Space Models
Maarten Grootendorst
·
newsletter.maartengrootendorst.com
·
almost 2 years ago
·
LLMs
Thinking about High-Quality Human Data
Lilian Weng
·
lilianweng.github.io
·
almost 2 years ago
·
LLMs
Generation configurations: temperature, top-k, top-p, and test time compute
Chip Huyen
·
huyenchip.com
·
almost 2 years ago
·
LLMs
Deep learning for single-cell sequencing: a microscope to see the diversity of cells
The Gradient
·
thegradient.pub
·
almost 2 years ago
·
LLMs
Book Update #2 - Hands-On Large Language Models
Maarten Grootendorst
·
newsletter.maartengrootendorst.com
·
about 2 years ago
·
LLMs
Salmon in the Loop
The Gradient
·
thegradient.pub
·
about 2 years ago
·
LLMs
BERTopic: What Is So Special About v0.16?
Maarten Grootendorst
·
newsletter.maartengrootendorst.com
·
about 2 years ago
·
LLMs
Six intuitions about large language models
Jason Wei
·
jasonwei.net
·
about 2 years ago
·
LLMs
Which Quantization Method is Right for You? (GPTQ vs. GGUF vs. AWQ)
Maarten Grootendorst
·
newsletter.maartengrootendorst.com
·
about 2 years ago
·
LLMs
Adversarial Attacks on LLMs
Lilian Weng
·
lilianweng.github.io
·
about 2 years ago
·
LLMs
Multimodality and Large Multimodal Models (LMMs)
Chip Huyen
·
huyenchip.com
·
about 2 years ago
·
LLMs
Introducing KeyLLM — Keyword Extraction with LLMs
Maarten Grootendorst
·
newsletter.maartengrootendorst.com
·
about 2 years ago
·
LLMs
An Introduction to the Problems of AI Consciousness
The Gradient
·
thegradient.pub
·
about 2 years ago
·
LLMs
3 Ways To Improve Your Large Language Model
Maarten Grootendorst
·
newsletter.maartengrootendorst.com
·
over 2 years ago
·
LLMs
Topic Modeling with Llama 2
Maarten Grootendorst
·
newsletter.maartengrootendorst.com
·
over 2 years ago
·
LLMs
Open challenges in LLM research
Chip Huyen
·
huyenchip.com
·
over 2 years ago
·
LLMs
Decoding Auto-GPT
Maarten Grootendorst
·
newsletter.maartengrootendorst.com
·
over 2 years ago
·
LLMs
LLM Powered Autonomous Agents
Lilian Weng
·
lilianweng.github.io
·
over 2 years ago
·
LLMs
Welcome!
Maarten Grootendorst
·
newsletter.maartengrootendorst.com
·
over 2 years ago
·
LLMs
Generative AI Strategy
Chip Huyen
·
huyenchip.com
·
over 2 years ago
·
LLMs
Common arguments regarding emergent abilities
Jason Wei
·
jasonwei.net
·
over 2 years ago
·
LLMs
Prompt Engineering
Lilian Weng
·
lilianweng.github.io
·
almost 3 years ago
·
LLMs
The Transformer Family Version 2.0
Lilian Weng
·
lilianweng.github.io
·
almost 3 years ago
·
LLMs
Research I enjoy
Jason Wei
·
jasonwei.net
·
almost 3 years ago
·
LLMs
137 emergent abilities of large language models
Jason Wei
·
jasonwei.net
·
about 3 years ago
·
LLMs
Generalized Visual Language Models
Lilian Weng
·
lilianweng.github.io
·
over 3 years ago
·
LLMs
Learning with not Enough Data Part 3: Data Generation
Lilian Weng
·
lilianweng.github.io
·
over 3 years ago
·
LLMs
Applying massive language models in the real world with Cohere
Jay Alammar
·
jalammar.github.io
·
almost 4 years ago
·
LLMs
The Illustrated Retrieval Transformer
Jay Alammar
·
jalammar.github.io
·
almost 4 years ago
·
LLMs
Reducing Toxicity in Language Models
Lilian Weng
·
lilianweng.github.io
·
almost 5 years ago
·
LLMs
Finding the Words to Say: Hidden State Visualizations for Language Models
Jay Alammar
·
jalammar.github.io
·
almost 5 years ago
·
LLMs
Controllable Neural Text Generation
Lilian Weng
·
lilianweng.github.io
·
almost 5 years ago
·
LLMs
Interfaces for Explaining Transformer Language Models
Jay Alammar
·
jalammar.github.io
·
about 5 years ago
·
LLMs
How GPT3 Works - Visualizations and Animations
Jay Alammar
·
jalammar.github.io
·
over 5 years ago
·
LLMs
A Benchmark for Evaluating Outcome-Driven Constraint Violations in Autonomous AI Agents
arXiv CS.AI
·
arxiv.org
·
1 day ago
·
LLMs
Safety Alignment of LMs via Non-cooperative Games
arXiv CS.AI
·
arxiv.org
·
1 day ago
·
LLMs
Uncovering Competency Gaps in Large Language Models and Their Benchmarks
arXiv CS.CL
·
arxiv.org
·
1 day ago
·
LLMs
TokSuite: Measuring the Impact of Tokenizer Choice on Language Model Behavior
arXiv CS.CL
·
arxiv.org
·
1 day ago
·
LLMs
Large Language Models Approach Expert Pedagogical Quality in Math Tutoring but Differ in Instructional and Linguistic Profiles
arXiv CS.CL
·
arxiv.org
·
1 day ago
·
LLMs
Investigating Model Editing for Unlearning in Large Language Models
arXiv CS.CL
·
arxiv.org
·
1 day ago
·
LLMs
Measuring Mechanistic Independence: Can Bias Be Removed Without Erasing Demographics?
arXiv CS.CL
·
arxiv.org
·
1 day ago
·
LLMs
Semantic Deception: When Reasoning Models Can't Compute an Addition
arXiv CS.CL
·
arxiv.org
·
1 day ago
·
LLMs
EssayCBM: Rubric-Aligned Concept Bottleneck Models for Transparent Essay Grading
arXiv CS.CL
·
arxiv.org
·
1 day ago
·
LLMs
MediEval: A Unified Medical Benchmark for Patient-Contextual and Knowledge-Grounded Reasoning in LLMs
arXiv CS.CL
·
arxiv.org
·
1 day ago
·
LLMs
Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
arXiv CS.CL
·
arxiv.org
·
1 day ago
·
LLMs
How important is Recall for Measuring Retrieval Quality?
arXiv CS.CL
·
arxiv.org
·
1 day ago
·
LLMs
Architectural Trade-offs in Small Language Models Under Compute Constraints
arXiv CS.CL
·
arxiv.org
·
1 day ago
·
LLMs
Where Did This Sentence Come From? Tracing Provenance in LLM Reasoning Distillation
arXiv CS.CL
·
arxiv.org
·
1 day ago
·
LLMs
Neural Probe-Based Hallucination Detection for Large Language Models
arXiv CS.CL
·
arxiv.org
·
1 day ago
·
LLMs
MultiMind at SemEval-2025 Task 7: Crosslingual Fact-Checked Claim Retrieval via Multi-Source Alignment
arXiv CS.CL
·
arxiv.org
·
1 day ago
·
LLMs
Reflection Pretraining Enables Token-Level Self-Correction in Biological Sequence Models
arXiv CS.CL
·
arxiv.org
·
1 day ago
·
LLMs
Automatic Replication of LLM Mistakes in Medical Conversations
arXiv CS.CL
·
arxiv.org
·
1 day ago
·
LLMs
Learning Evolving Latent Strategies for Multi-Agent Language Systems without Model Fine-Tuning
arXiv CS.LG
·
arxiv.org
·
1 day ago
·
LLMs
Enhancing Lung Cancer Treatment Outcome Prediction through Semantic Feature Engineering Using Large Language Models
arXiv CS.LG
·
arxiv.org
·
1 day ago
·
LLMs
Real Time Detection and Quantitative Analysis of Spurious Forgetting in Continual Learning
arXiv CS.LG
·
arxiv.org
·
1 day ago
·
LLMs
Data-Free Pruning of Self-Attention Layers in LLMs
arXiv CS.LG
·
arxiv.org
·
1 day ago
·
LLMs
Managing the Stochastic: Foundations of Learning in Neuro-Symbolic Systems for Software Engineering
arXiv CS.LG
·
arxiv.org
·
1 day ago
·
LLMs
HyDRA: Hierarchical and Dynamic Rank Adaptation for Mobile Vision Language Model
arXiv CS.LG
·
arxiv.org
·
1 day ago
·
LLMs
Revisiting the Learning Objectives of Vision-Language Reward Models
arXiv CS.LG
·
arxiv.org
·
1 day ago
·
LLMs
PHOTON: Hierarchical Autoregressive Modeling for Lightspeed and Memory-Efficient Language Generation
arXiv CS.LG
·
arxiv.org
·
1 day ago
·
LLMs
FEM-Bench: A Structured Scientific Reasoning Benchmark for Evaluating Code-Generating LLMs
arXiv CS.LG
·
arxiv.org
·
1 day ago
·
LLMs
BitRL-Light: 1-bit LLM Agents with Deep Reinforcement Learning for Energy-Efficient Smart Home Lighting Optimization
arXiv CS.AI
·
arxiv.org
·
1 day ago
·
LLMs
MegaRAG: Multimodal Knowledge Graph-Based Retrieval Augmented Generation
arXiv CS.AI
·
arxiv.org
·
1 day ago
·
LLMs
MicroProbe: Efficient Reliability Assessment for Foundation Models with Minimal Data
arXiv CS.AI
·
arxiv.org
·
1 day ago
·
LLMs
Erkang-Diagnosis-1.1 Technical Report
arXiv CS.AI
·
arxiv.org
·
1 day ago
·
LLMs
Reasoning Relay: Evaluating Stability and Interchangeability of Large Language Models in Mathematical Reasoning
arXiv CS.AI
·
arxiv.org
·
1 day ago
·
LLMs
AIAuditTrack: A Framework for AI Security system
arXiv CS.AI
·
arxiv.org
·
1 day ago
·
LLMs
Memory Bear AI A Breakthrough from Memory to Cognition Toward Artificial General Intelligence
arXiv CS.AI
·
arxiv.org
·
1 day ago
·
LLMs
AI-Driven Decision-Making System for Hiring Process
arXiv CS.AI
·
arxiv.org
·
1 day ago
·
LLMs
From Fake Focus to Real Precision: Confusion-Driven Adversarial Attention Learning in Transformers
arXiv CS.AI
·
arxiv.org
·
1 day ago
·
LLMs
Quantifying Laziness, Decoding Suboptimality, and Context Degradation in Large Language Models
arXiv CS.AI
·
arxiv.org
·
1 day ago
·
LLMs
Eidoku: A Neuro-Symbolic Verification Gate for LLM Reasoning via Structural Constraint Satisfaction
arXiv CS.AI
·
arxiv.org
·
1 day ago
·
LLMs
AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent
arXiv CS.AI
·
arxiv.org
·
1 day ago
·
LLMs