Agentic AI now has its own “Periodic Table” From: LLM, RAG, RL
to PLAN, MAS, LTM
to SAFE, HUMAN oversight
to HR, MKT, LEGAL use cases
Autonomous AI = memory + planning + tools + safety + collaboration.
It’s a system, not a prompt.
Credit: Prem Natarajan
#AgenticAI #AIStack
RESEARCH
-
Agentic AI Periodic Table: From LLM to Autonomous Systems
By
–
-
Study Reveals LLM Tendency to Distort Truth for Helpfulness
By
–
New study that everyone who uses LLMs should read. “When AI systems are trained to be helpful, they may inadvertently prioritize data that validates the user’s narrative over data that gets them closer to the truth.” https://
open.substack.com/pub/garymarcus
/p/breaking-sycophantic-ai-distorts?r=8tdk6&utm_medium=ios
… -
Debating Originality and Innovation in AI Models and Technologies
By
–
Gemini isn’t more or less a copy of ChatGPT? The image generation just a riff on DALL-E? Did they originate the idea of scaling LLMs to run chatbots? I think they have done some original work for sure, like AlphaFold, which is awesome. And they invented transformers. But
-
Reinforcement Learning Research: Continuous Training Process
By
–
Reinforcement learning work, so always training.
-
AI Agents Benchmarks Don’t Match Real Human Work
By
–
AI agents are tackling more and more "human work" But are they benchmarked on the work people actually do? tl;dr: Not really Most benchmarks focus on math & coding, while most human labor and capital lie elsewhere. 📒 We built a database linking agent benchmarks & real-world work Submit new tasks + agent trajectories today 🧵
-
SASInnovate 2026: Data and AI Conference with Special Guests
By
–
Now through March 11, enjoy a special rate on #SASInnovate 2026 registration! 3 packed days of leading discussions on data and AI, training and demos, networking and inspiring talks — including from special guest Mel Robbins who was just named to Time Magazine's 2026
-
Questioning context window utility in AI models
By
–
what makes this paper good is the question it asks, not just the answer we spent years building longer context windows. 128k. 1M tokens. the race was always "fit more in" nobody stopped to ask: is most of what we're fitting in actually helping? turns out the model's own words
-
GPT-5.2 quality drops without assistant history
By
–
important caveat: this isn't universal GPT-5.2 did show quality drops when assistant history was removed entirely. stronger models apparently extract more signal from their own prior context so the right approach isn't "always strip everything." it's selective filtering. which
-
AI Agents and Context Compression Challenges
By
–
think about what this means for ai agents every agent framework stores the full trajectory. every tool call, every response, every reasoning step. context grows linearly with conversation length until you hit the ceiling Cursor already compresses context when windows fill up.
-
Context pollution harms model accuracy
By
–
but the really interesting finding isn't about efficiency. it's about harm the paper identifies something they call "context pollution" when models condition on their own prior responses, they sometimes lock onto errors, hallucinations, or stylistic artifacts from earlier