Modern AI = 5 pillars Generative AI (create) LLMs (reason) RAG (ground + verify) AI Agents (act) Agentic AI (coordinate + scale) We’re moving from AI that answers → AI that executes outcomes. Which pillar wins next? #AI #GenerativeAI #LLMs #RAG
GENERATIVE AI
-
Krea iPad Voice Mode Enables Real-Time Drawing Interaction
By
–
introducing Voice Mode.
— KREA AI (@krea_ai) 2 mars 2026
speak as you draw and get changes in real-time.
available now in Krea iPad. pic.twitter.com/c6mHHjupmWintroducing Voice Mode. speak as you draw and get changes in real-time. available now in Krea iPad.
-
Google Releases Nano Banana 2 on Pollo AI
By
–
Google recently dropped Nano Banana 2, and it is now live on Pollo AI. Nano Banana 2 is the model that combines Flash speed with pro-level image quality, subject consistency, multilingual text rendering, and wide-format support in a single generation. Test it out on @itsPolloAI
-
Context engineering is the new bottleneck
By
–
the broader observation matters more than this specific paper. context engineering is quietly becoming the real bottleneck. not model capability, not training data, not inference cost. the unglamorous plumbing of what information reaches the model, when, and how. Anthropic
-
Software Architecture Proposal for AIGNE Framework
By
–
to be clear about what this is and isn't. this is a software architecture proposal, not a benchmark-beating system. the implementation is in the AIGNE framework with two exemplars: a memory-enabled chatbot and an MCP-based GitHub assistant. proof of concept, not production at
-
Three-Stage Pipeline Between Filesystem and Token Window
By
–
between the filesystem and the token window sits a three-stage pipeline. the context constructor selects and compresses context from the filesystem into a token-budget-aware input. it queries recency and relevance metadata, applies summarization, and produces a manifest
-
Three Tiers of Persistent Context Explained
By
–
the paper defines three tiers of persistent context, each with different lifecycles. scratchpads (/context/pad/) are temporary working notes scoped to a task. think of them as the agent's rough draft space. episodic memory (/context/memory/episodic/) holds session-bounded
-
Agent frameworks’ context handling flaws
By
–
the problem is real and underappreciated. right now, most agent frameworks handle context like this: load memory at session start. stuff it into the prompt. when the window fills, summarize and compress. hope the important parts survive. the paper calls this out directly. once
-
Unix principle applied to AI context
By
–
"everything is a file" becomes "everything is context." CSIRO Data61 and ArcBlock published a paper applying the oldest Unix principle to the newest AI problem. they propose treating memory, tools, knowledge, and human input as a mounted filesystem that agents browse at runtime
-
Reasoning requires basic knowledge for effective search guidance
By
–
You still need a bit of knowledge in any reasoning, just to guide you in where to look. For instance, you'll do better search on geopolitics if you know a bit about the general trends. Qwen just demonstrated that this base level of knowledge can be attained in a very compact