MeMo: Memory as a Model
Paper: https://
arxiv.org/abs/2605.15156
AI
-
MeMo paper: Memory as a Model on arXiv
By
–
-
MEMO: Store fresh knowledge in separate memory model without retraining
By
–
Cool, your AI could learn new information without ever retraining its core brain! MIT, A*STAR, NUS, and Liquid AI researchers introduce MEMO (Memory as a Model). Instead of fine-tuning the LLM, MEMO stores fresh knowledge in a separate "memory" model. Think of it like adding a
-
Estimated energy and water for an LLM solving an Erdös problem
By
–
If this is true, using the best public estimates we have of LLM resource use, solving this Erdos problem took 0.6–6.3 kWh of electricity and about 3–31 liters of water. So that is less than three almonds worth of water and the electricity equivalent of 2-20 miles of EV driving.
-
Agent Swarms for Apps and Automations
By
–
🚨 AGENT SWARMS – BUILD COMPLEX APPS AND AUTOMATIONS WITH ONE PROMPT
— Abacus.AI (@abacusai) 21 mai 2026
Combine Gemini 3.1 Pro, Opus 4.7 and GPT 5.5 to create complex multi-agent systems
Each agent excels at a particular task – coding, testing, mobile app, research and monitoring
Master agent orchestrates… pic.twitter.com/QGfgUPNT84AGENT SWARMS – BUILD COMPLEX APPS AND AUTOMATIONS WITH A SINGLE PROMPT Combine Gemini 3.1 Pro, Opus 4.7, and GPT 5.5 to create advanced multi-agent systems. Each agent specializes in a specific task—coding, testing, mobile app development, research, and monitoring. A master agent orchestrates the workflow.
-
Free online bible for running LLMs locally on any hardware
By
–
DROP EVERYTHING The bible for running LLMs locally is now available online to read for free Covers what to use on – Laptop / edge / odd hardware
– Mac-first workflows
– Single RTX GPUs
– 2-4+ NVIDIA / CUDA GPUs
– General production serving
– Long-context / MoE / routing
– -
Which AI labs will prioritize social science research?
By
–
Math is easy* because it has verifiable outputs and few messy judgement choices to make. Which AI labs have the guts to make advancing social science a priority? It may actually do more for human flourishing to unlock sociology, econ & psych reseach. * For AIs, not for humans
-
SpaceX’s AI TAM vs. Anthropic, OpenAI, and Google IPOs
By
–
If the TAM for @SpaceX
's IPO is $26.5 trillion in AI, what's the right number for @AnthropicAI
, @OpenAI and @Google ? -
Excitement over AGI takeoff with caveat from multiple companies
By
–
As excited as I am that a takeoff seems to have begun and we are entering a golden age of science, one thing remains: I'm hearing more and more from all sides that AGI is within reach. This applies to Google (AGI, Physical AGI), as well as OpenAI and Anthropic. The only caveat:
-
FFN Architecture Patterns in Mixture-of-Experts Models
By
–
It’s interesting. I’ve seen hidden -> wider -> hidden FFNs and hidden -> narrower -> hidden FFNs.
But Command A+ seems tu use 4096 -> 4096 -> 4096 for each expert FFN, which I haven’t seen before (as far as I remember) -
Technical training efficiency insights from the Tiny Aya model report
By
–
I think so. In their 3.35B Tiny Aya report, they say "We use parallel Transformer blocks, which lead to a signifi-
cant improvement in training efficiency without hurting model quality."