An AI users converse with. They rate their and it's statements. The company that owns it groups similar statements researching about the groups. And rewards the user higher if thier ratings are high than if low for breakthroughs in the companys research.

Tesla FSD is 🪄. Need to be able to converse w/ Grok like we can with an Uber driver: “Hey Grok, turn right here.” “Drop us off right here, we'll walk due to traffic.” “Drop at entrance first, then park far away.” @Tesla_AI

🚨WHAT THE HELL?!!!! Divers doing a ROUTINE maintenance check at the Converse Reservoir dam in Mobile, AL... ...just found an underwater IED!!!! Apparently a grenade-type bomb was sitting submerged at the bottom of a dam that holds an entire city's DRINKING WATER. It took FIVE agencies: the FBI, ALEA, the Sheriff, Mobile PD, and a maritime render-safe team, to pull it out and detonate it. Someone put a BOMB in our water supply... WHERE IS THE NATIONAL COVERAGE?!!!

President Xi Jinping held a private meeting with U.S. President Donald J. Trump at Zhongnanhai. The two heads of state strolled and conversed, and paused from time to time to admire the stalwart ancient trees and Chinese roses.

✨ what a year ✨ CHROMAKOPIA world tour 105 shows dont tap the glass marty supreme 11th camp flog gnaw bottega veneta campaign 6 grammy nominations sugar on my tongue F40 sydney, australia golf wang flagship P.O.V with clipse ended le FLEUR* apple artist of the year fortnite arizona green tea can converse joggers, bronco and naut 1 and so much more. thank you for your eyes and ears. ✨

This new Nvidia paper is huge for model routing and the future of inference: re-using the KV cache across different LLMs. One of the greatest challenge in model routing during long-horizon agent settings is that the cache does not transfer across different models. As a result, naively switching models without KV-cache-awareness will result in wasting more money. Conversely, transferring the KV cache across models significantly expands the total amount of savings that can be achieved. This paper is a great step in that direction. Congrats to Taekyung Heo, Rasoul Shafipour, Ritchie Zhao, Maximilian Golub, @MMKamani7, @Ritika_Borkar, Makesh Tarun Chandran, Pantea Zardoshti, and Bita Darvish Rouhani. Two questions: 1. Do you plan to investigate cross-family transfer? I saw this in the future work section but curious to learn more about your intuitions on the opportunities and challenges here. 2. What was the reason for focusing mostly on small to large model transfers and not large to small?

🧭 Reaching for LangGraph by default? This paper is a practitioner guide that separates where graph orchestration truly helps from where it just gets in the way. The authors argue LangGraph adds value not through model quality but through durable orchestration and governance. So it earns its place when a workflow must pause and resume, or when the next step depends on explicit state like risk, evidence quality, or retry count. Conversely, if a single prompt plus one tool call suffices, keep it simple with a plain SDK, they warn against overuse. The thesis is made concrete with three runnable recipes: SQL analytics that self-repairs from validation and execution errors; a fail-closed RAG that returns "insufficient" instead of fabricating when evidence is weak; and a HITL flow that interrupts only high-risk cases for human review. Each uses typed state, conditional edges, and checkpoints to lift repair and approval out of implicit prompts into testable, explicit steps (with a warning that removing the checkpointer breaks pause/resume, so high-risk cases never complete). Tool selection is crisp too: ReAct for simple cases, schema-first for structured extraction, DSPy for prompt optimization, LangGraph when branching and audit matter. By deliberately skipping benchmarks to discuss when engineering shape changes, Graph-Based Agentic AI with LangGraph is a solid map for design decisions. 🔗 #LangGraph# #AIAgents#