#ai (37 posts)

2025

Apr 25

o3/o4-mini: Smart, but Practically Unusable

Jan 24

OpenAI ChatGPT Operator Browser "Agent" Product

2024

Dec 24

The DNA of AI Agents: Common Patterns in Recent Design Principles

Sep 13

Some Reflection on What OpenAI o1 Reasoning Launch Means

Aug 16

Llama-3.1-Minitron 4B is a Smaller and Accurate LLM

Aug 16

Prompt Caching with Anthropic Claude

Jul 24

🐐 Llama 3.1 405B Matches Or Beats The Top Foundation Models

Jul 22

Llama 3.1 Leaks: SoTA Open Model 405B & What We Know So Far

Jul 16

Co-Intelligence: Living and Working with AI - A Book Review

Jul 14

Vibe Checking Claude 3.5, DeepSeek-Coder-V2, and GPT-4o for "Alien" Coding Skills

Jun 21

Claude 3.5 Sonnet

May 16

The Bitter Lesson by Rich Sutton

May 15

Google Gemini 1.5 Vibe Check

May 15

The Assembly Language Period of LLMs and Generative AI

May 14

Deconstructing GPT-4o

May 14

GPT-4o: HER Went From Science Fiction to Reality

May 14

Voice AI Research

May 12

May 12

Generative AI Engineering

May 12

State of GPT 2023

May 10

Tradeoffs Between Long-Context LLM and RAG

Apr 27

Evaluating Llama 3 on Code Tasks

Apr 26

The Intuition behind Rotary Positional Embedding (RoPE)

Apr 19

Meta releases Llama 3 Large Language Models (LLMs) 🦙

Apr 13

Rebutting Devin: "First AI Software Engineer" Claim is Not True

Apr 12

AI Agents and Agentic Behavior

Jan 24

Early Thoughts on Large Language Models

Jan 22

What Defines an Advanced AI Coding Assistant?

2023

Aug 11

Leaked System Prompts

Jul 27

Llama2.c — The rise of micro-LLMs

Mar 22

Creating a chatbot using Alpaca native and LangChain

Mar 13

4 Steps in Running LLaMA-7B on a M1 MacBook

Feb 14

HuggingFace Transformers inference for Alpaca

Feb 14

Hacking LLaMA Models

2020

Jul 19

GPT-3 Application Ideas

2019

Jul 17

Singapore A.I. Day 2019

2017

May 20

Computer Science and Mathematical Reasoning