This article is about the 79th episode of the Attack on Titan anime. For the manga chapter of the same name, see Memories of the Future (Chapter). Memories of the Future (未来の記憶 Mirai no Kioku?) is...
OpenAI Developers on Twitter / X
Last week, we released a preview of memories in Codex.Today, we’re expanding the experiment with Chronicle, which improves memories using recent screen context.Now, Codex can help with what you’ve been working on without you restating context. pic.twitter.com/b3p8I5eXOy— OpenAI Developers (@OpenAIDevs) April 20, 2026
Titans + MIRAS: Helping AI have long-term memory
Ali Behrouz, Student Researcher, Meisam Razaviyayn, Staff Researcher, and Vahab Mirrokni, VP and Google Fellow, Google Research
alphaXiv on Twitter / X
"Metis: Memory Foundation Model"Most AI agents still use memory as an external RAG-style module, so the model retrieves old text instead of actually remembering.This paper makes memory native to the Transformer. So past interactions are compressed into dynamic layer states… pic.twitter.com/YylDDXGX3G— alphaXiv (@askalphaxiv) July 31, 2026
25 Best Psychological Anime that'll Make You Think Deep - MyAnimeGo
In the vast and diverse world of anime, there is a genre that delves into the intricate workings of the human mind, offering captivating stories that leave viewers pondering long after the final episode. Psychological anime explores the depths of emotions, thoughts, and motivations through complex characters and mind-bending narratives. These thought-provoking shows challenge conventional […]
A Better Memory Bank - Convergence.ninja
As my projects grow and evolve, I've come to realize that a simple snapshot of the "current state" isn't always enough. To truly understand a project's journey—the why behind the what—you need context. You need history. My original Memory Bank was great for telling me where I was, but it wasn't so great at telling me how I got there. That's why I decided it was time for an upgrade.
Memory Models: Towards Agents That Learn
Agents that truly learn from experience will be powered by memory models: models that create and curate token-space memory across model generations, trained with memory-native RL.
To Make Sense of the Present, Brains May Predict the Future | Quanta Magazine
A controversial theory suggests that perception, motor control, memory and other brain functions all depend on comparisons between ongoing actual experiences and the brain’s modeled expectations.
Obsidian — Your AI second brain isn’t memory — and here’s the architecture that actually is
There is a story being told everywhere right now, and it is not quite a lie, but it has stopped being honest. The story goes: install…
Nebula AI - Memory Layer for AI Agents
Nebula is the AI memory layer turning every interaction into conceptual knowledge that continuously improves LLM applications.
Woah. Letta vs Mem0. (For AI memory nerds)
365 votes, 55 comments. I’m an absolute AI memory nerd, and have probably read every proposal made about memory, and demoed virtually all of the…
Roblox Dream Diary
A series of microgames made over the course of one year. Walk through a lit doorway to be transported to that dream. Some dreams have buttons in the lower right corner that will transport you back; those that do not will do so automatically. In order of construction; Shell Museum Atrium Tornadoes Toro Cany## ###es Pluto Boat in the Cottonwoods Neon Industrial Channel Train It's Time (cw: themes of death of ##### ####) Herons If you want a place to start I'd suggest; Pluto, Train, It's Time, Herons, or Domes.
An Empirical Study of Example Forgetting during Deep Neural Network Learning
Inspired by the phenomenon of catastrophic forgetting, we investigate the learning dynamics of neural networks as they train on single classification tasks. Our goal is to understand whether a related phenomenon occurs when data does not undergo a clear distributional shift. We define a “forgetting event” to have occurred when an individual training example transitions […]
Layers of Memory, Layers of Compression
AI superpower = strategic amnesia. Letta caches memory like a CPU, Anthropic spreads it across agent swarms, Cognition warns of chaos. Curious how forgetting makes machines smarter? Dive in.
"Efforts to predict the future go hand-in-hand with efforts to control it. Rebel against tyrannical predictions. Let's be brave enough to imagine and fight for a better world." 💙
Carissa Véliz
A culture of divination has grown all around us - from machine learning, to prediction markets, and forecasting of all kinds, not to mention psychics and astrology. But have you ever wondered what, exactly, is in a prediction? TED talk: youtube.com/watch?v=OS4wHmKtH-Q #PROPHECY #authors
