This note is about the self-awareness assumption we don't talk enough about, and which I think we need to address to ultimately understand intelligence and AI safety. RL agents have the action/observation split baked in at the architecture level. The action space A and
RESEARCH
-
Detecting Machine Failures Versus Understanding How to Fix Them
By
–
The distinction between knowing a machine might fail versus knowing exactly how to fix it is huge.
-
NVIDIA Earth-2 AI Models Transform Satellite Data Into Life-Saving Forecasts
By
–
🌍 Real-time data is the ultimate tool for Earth Day.
— NVIDIA AI (@NVIDIAAI) 22 avril 2026
NVIDIA Earth-2 models like HealDA, built with collaboration from @MITREcorp and @NOAA, turn satellite observations into life-saving forecasts in just minutes.
We’re moving past physics modeling alone to on-demand AI that… pic.twitter.com/ByzNjTOOMBReal-time data is the ultimate tool for Earth Day. NVIDIA Earth-2 models like HealDA, built with collaboration from @MITREcorp and @NOAA
, turn satellite observations into life-saving forecasts in just minutes. We’re moving past physics modeling alone to on-demand AI that -
Token Role Markers Enable Context Attribution in LLM Chatbots
By
–
We convert LLMs into chatbots by using markers, eg User and Assistant: User: What's the capital of France?
Assistant: Paris.
User: What did I just say? the "I just said" attribution works because the tokens are cleanly labeled with role markers. But strip the markers and -
Kimi K2.6: 1T-Parameter Open Model Achieves Agentic Coding
By
–
Kimi K2.6 is live on Replicate. @Kimi_Moonshot 's new 1T-parameter open model ran autonomously for 13 hours to refactor an 8-year-old trading engine — 4,000+ lines, 1,000+ tool calls, 185% throughput gain. Open weights. Agentic coding that actually finishes.
-
CoInteract: Physically-Consistent Human-Object Interaction Video Synthesis
By
–
CoInteract
— AK (@_akhaliq) 22 avril 2026
Physically-Consistent Human-Object Interaction Video Synthesis via Spatially-Structured Co-Generation
paper: https://t.co/sqbYFatpqg pic.twitter.com/ZSRChCRfpKCoInteract Physically-Consistent Human-Object Interaction Synthesis via Spatially-Structured Co-Generation paper: https://
huggingface.co/papers/2604.19
636
… -
Qwen-based Model Achieves Pareto Optimality in Accuracy-Cost
By
–
We’ve post trained a model on top of Qwen that achieves Pareto optimality on accuracy-cost curves. Unlike our previous post trained models, this model has been trained to be good at search and tool calls simultaneously, allowing us to unify the tool call router and
-
Perplexity’s Pipeline Improves Base Model Accuracy and Efficiency
By
–
This pipeline is why the same base model produces more accurate, better-cited, and more efficient answers inside Perplexity than out of the box. Read our research:
-
Reward Design Balances Correctness Preference Efficiency
By
–
Our reward design combines correctness, preference, and efficiency. Preference only counts when the answer is correct. This keeps the model from optimizing for better-sounding wrong answers.
-
Fine-tuning and On-Policy RL for Model Optimization
By
–
We first fine-tune the model to follow instructions, stay within guardrails, and keep language consistent. Then we run on‑policy RL to improve search accuracy and tool efficiency while preserving those behaviors.