We recommend sonnet 4.5 for everything — you get more rate limits with it, and it’s more intelligent for coding tasks. Re:hostile, specific examples would be helpful to debug
INNOVATION
-

Enterprise Leaders Ask Key Questions on AI, 5G, IoT
By
–
👉 These themes – AI+, Connected Industries, and Connected Enablers – speak directly to the questions every enterprise leader is asking. #MWC25 Las Vegas #AI #5G #IoT #AgenticAI @MWCHub @CTIA @GSMA https://t.co/6kr7UVj3ye pic.twitter.com/st3b04wHGj
— Harold Sinnott #MWC26 (@HaroldSinnott) 12 octobre 2025These themes – AI+, Connected Industries, and Connected Enablers – speak directly to the questions every enterprise leader is asking. #MWC25 Las Vegas #AI #5G #IoT #AgenticAI @MWCHub @CTIA @GSMA
-
Artificial Hippocampus Networks: RNN Memory for Transformers
By
–
9. Artificial Hippocampus Networks Adds a fixed-size recurrent memory to sliding-window Transformers, compressing evicted KV into RNN-like states (Mamba2/DN/GDN) trained via self-distillation for long-context efficiency with constant cache and near-linear compute.
-

Mem-Agent: 4B LLM with Persistent Memory via GSPO
By
–
8. mem-agent mem-agent is a 4B-parameter LLM trained with GSPO reinforcement learning to develop persistent memory using a scaffold of Python tools and markdown files.
-

ArcMemo: Memory Framework for Abstract Reasoning Tasks
By
–
7. Abstract Reasoning Composition UC San Diego and UMD propose ArcMemo, a test-time memory framework that distills reusable concepts from solution traces, stores them in natural language, and retrieves a relevant subset on future queries.
-
Markovian Thinker: RL Environment for LLM State Management
By
–
6. The Markovian Thinker
— DAIR.AI (@dair_ai) 12 octobre 2025
A new RL thinking environment that keeps an LLM’s effective state constant by chunking long chains of thought and carrying over only a short textual state between chunks.https://t.co/mqXfF1XG6h6. The Markovian Thinker A new RL thinking environment that keeps an LLM’s effective state constant by chunking long chains of thought and carrying over only a short textual state between chunks.
-

Agentic Context Engineering: Modular Framework for LLM Playbooks
By
–
3. Agentic Context Engineering (ACE) Presents a modular context-engineering framework that grows and refines an LLM’s working context like a playbook, not a terse prompt.
-

Gene therapy restores hearing in deaf children via one-shot treatment
By
–
New @NEJM One-shot gene therapy for a type of congenital deafness enabled some children to hear for the first time, and 3 of 12 kids achieved normal hearing http://
nejm.org/doi/full/10.10
56/NEJMoa2400521
… -
Qwen 3 release questioned technical report limitations
By
–
I think the only one I might question the significance of in your list is Qwen 3. They didn't even release a base model. The technical report was quite disappointing as well.
-

AI and Immersive Tech Reshape Sales and Customer Interactions
By
–
The convergence of emerging technologies such as AI, immersive interfaces, and digital representations of people and customers will progressively redefine the dynamics of sales, shaping more adaptive, personalized, and emotionally aware interactions. Microblog by @antgrasso