Winston

Caught in a dilemma 1. Love Notion's attributes and DIY databases 2. Yet I love graph databases and their contextual backlinking - as well as the ability to thread. I can't figure out which one I love more. I wish both were present in a single app.

Sad to see that AI labs are focusing less on voice. Gemini Voice uses 2 Flash Grok Voice uses 2.0 ChatGPT uses 4o

🚨 This might be the biggest leap in AI agents since ReAct. Researchers just dropped DeepAgent a reasoning model that can think, discover tools, and act completely on its own. No pre-scripted workflows. No fixed tool lists. Just pure autonomous reasoning. It introduces something wild called Memory Folding the agent literally “compresses” its past thoughts into structured episodic, working, and tool memories… like a digital brain taking a breath before thinking again. They also built a new RL method called ToolPO, which rewards the agent not just for finishing tasks, but for how it used tools along the way. The results? DeepAgent beats GPT-4-level agents on almost every benchmark WebShop, ALFWorld, GAIA even with open-set tools it’s never seen. It’s the first real step toward general reasoning agents that can operate like humans remembering, adapting, and learning how to think. The agent era just leveled up.

holy sh*t... your llm remembers everything you typed 🤯 researchers just proved you can recover the EXACT input text from a language model's hidden states. not similar text. not approximate. the actual words you typed. here's what they found: • transformer language models are mathematically injective • different inputs = different hidden states (with probability 1) • this isn't a coincidence or training artifact, it's structural • they built SIPIT, an algorithm that inverts the model in linear time • tested on billions of prompts across GPT-2, Gemma, Llama • 100% exact recovery rate. zero collisions found. the math is airtight. transformers are real-analytic functions, which means collisions can only happen on measure-zero parameter sets. at random init? probability zero. after gradient descent? still zero. you cannot accidentally make these models lossy. the information doesn't compress. it doesn't abstract. it just transforms into a different representation that perfectly preserves every token. your prompt never leaves the model. it just lives in 768 dimensions instead of text. this changes everything about how we think about llm internals, interpretability, and what "representations" actually mean.