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
LLMS
-
AI Output Limits Increased Based on User Feedback
By
–
Yep just output. We used to have a lower max output limit but people asked for a higher limit
-
Webscale-RL: 1.2M QA Pairs for Web-Scale Reinforcement Learning
By
–
10. Webscale-RL Webscale-RL introduces a scalable data pipeline that transforms web-scale pretraining text into over 1.2M diverse, verifiable QA pairs for reinforcement learning across 9+ domains.
-
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.
-
Scaling Long-Horizon Reasoning Without Step Labels
By
–
5. Reasoning over Longer Horizons via RL The authors show that you can scale long-horizon reasoning without step labels or heavy scaffolding.
-
Inoculation Prompting: Safety Technique for Flawed Training Data
By
–
4. Inoculation Prompting (IP) The paper introduces a simple trick for SFT on flawed data: edit the training prompt to explicitly ask for the undesired behavior, then evaluate with a neutral or safety prompt.
-
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.