Google has published a paper that might end the transformer era.
For the last 7 years, every major AI, ChatGPT, Claude, Gemini, has been built on the exact same architecture: The Transformer.
But Transformers have a fatal flaw.
To remember context, they have to process every single word against every other word. Itâs called quadratic complexity. As your prompt gets longer, the compute cost explodes.
The alternative is the old-school RNN (Recurrent Neural Network). RNNs are incredibly cheap and fast, but they have a fixed memory size. If you give them a long document, they get amnesia.
Until today.
Google researchers published Memory Caching: RNNs with Growing Memory.
And it fixes the biggest bottleneck in AI.
Instead of an RNN having a fixed, rigid memory that constantly overwrites itself, Google gave it a "save" button.
The technique allows the RNN to cache checkpoints of its hidden states as it reads.
The memory capacity of the RNN can now dynamically grow as the sequence gets longer.
They built four different variants, including sparse selective mechanisms where the AI actively chooses exactly which checkpoints matter most.
The results rewrite the rules of efficiency.
On long-context understanding and recall-intensive tasks, these new Memory-Cached RNNs closed the gap with Transformers.
They achieved competitive accuracy without the explosive, quadratic compute cost. It perfectly bridges the gap between the cheap efficiency of an RNN and the massive capability of a Transformer.
We have spent billions scaling Transformers because we thought they were the only way an AI could remember a long conversation.
But Google just proved we don't need to process the whole history every single time.
We just needed a smarter cache.
My friend Milla Jovovich and I spent months creating an AI memory system with Claude. It just posted a perfect score on the standard benchmark - beating every product in the space, free or paid.
It's called MemPalace, and it works nothing like anything else out there.
Instead of sending your data to a background agent in the cloud, it mines your conversations locally and organizes them into a palace - a structured architecture with wings, halls, and rooms that mirrors how human memory actually works.
Here is what that gets you:
â Your AI knows who you are before you type a single word - family, projects, preferences, loaded in ~120 tokens
â Palace architecture organizes memories by domain and type - not a flat list of facts, a navigable structure
â Semantic search across months of conversations finds the answer in position 1 or 2
â AAAK compression fits your entire life context into 120 tokens - 30x lossless compression any LLM reads natively
â Contradiction detection catches wrong names, wrong pronouns, wrong ages before you ever see them
The benchmarks:
100% recall on LongMemEval â first perfect score ever recorded. 500/500 questions. Every question type at 100%.
92.9% on ConvoMem â more than 2x Mem0's score.
100% on LoCoMo â every multi-hop reasoning category, including temporal inference which stumps most systems.
No API key. No cloud. No subscription. One dependency. Runs on your machine. Your memories never leave.
MIT License. 100% Open Source.
https://t.co/KggwTqijmD
Google lancou Gemma 4 com licenca Apache 2.0
Pela PRIMEIRA VEZ um modelo do Google e verdadeiramente open-source
A familia:
- 31B denso: qualidade maxima no seu PC
- 26B MoE (3.8B ativos): velocidade absurda
- 4B e 2B: celulares e IoT
- 250K tokens de contexto
- Audio + visao nativos
- Suporte a ferramentas (agentes)
400 milhoes de downloads do Gemma. 100K variantes. E agora Apache 2.0
Construido com a mesma pesquisa do Gemini 3, rodando no SEU hardware
A era dos modelos locais acabou de ganhar o maior aliado possivel
Robo que faz coleta de sangue sozinho. Ja esta em hospitais na Europa.
Ultrassom pra achar a veia, precisao sub-milimetrica, funciona em qualquer paciente. A agulha fica escondida pra nao causar ansiedade.
Um supervisor monitora ate 3 robos ao mesmo tempo. Num mundo com falta cronica de profissionais de saude, isso muda o jogo
You can now enable Claude to use your computer to complete tasks.
It opens your apps, navigates your browser, fills in spreadsheetsâanything you'd do sitting at your desk.
Research preview in Claude Cowork and Claude Code, macOS only.