you need to be swarm maxxing anon
AGENTS
-
Agency Surpasses Intelligence in the Age of AI
By
–
The modern age has richly rewarded people with a combination of high intelligence and high agency. Now that many aspects of intelligence are successfully being automated, it seems likely that people with relatively lower intelligence but exceptional agency will come into their own if they are willing to egolessly accept AI advice. Imagine a ruthless criminal that completely trusts everything their always-on AI glasses are telling them, knowing that it is carefully looking out for their best interests and isn't scheming to betray them. [Translated from EN to English]
→ View original post on X — @id_aa_carmack, 2026-02-12 18:46 UTC
-
Fast and Frontier AI Models Converging with Parallel Reasoning
By
–
Over time, the experience of fast models like Codex-Spark and deeper frontier models like GPT-5.3-Codex will start to blend. You can imagine instant interactions in the foreground, deeper reasoning and sub-agents running in parallel in the background.
-
Try SciSpace Agent for Paper Discovery, Analysis, and Summaries
By
–
8/
Try @SciSpace now! Where to start? Get your own account and try these use cases for reviewing papers using the Agent: ● Discover: Find relevant papers instantly
● Analyze: Multi-PDF with citation support + Mendeley
● Write & Cite: Generate a structured summary
● -
SciSpace Agent Adds Mendeley Integration for Research Workflows
By
–
6/
(3) Mendeley Integration — Users can connect their Mendeley account to the @SciSpace Agent. As with Zotero, this integration fills the gap between reference management and research work (literature discovery, paper analysis, writing, citations, and reporting) in one research -
SciSpace launches research and Biomed AI agents within agent suite
By
–
2/
The current @SciSpace suite includes a user platform and a collection of AI tools for two major agents (supported by over 600 agents in total):
● SciSpace Agent — A wide-spectrum research assistant that handles end-to-end research tasks.
● BioMed Agent — A comprehensive AI -
$3M Grants for Open Source Agentic AI Benchmarks
By
–
We’re incredibly excited to launch Open Benchmarks Grants, a new program committing $3M in grants to fund new open source benchmarks advancing agentic AI.
— Snorkel AI (@SnorkelAI) 12 février 2026
We’re partnering up with @HuggingFace, @togethercompute, @PrimeIntellect, Factory HQ, @harborframework, and @PyTorch to… pic.twitter.com/4sXnfHitAOWe’re incredibly excited to launch Open Benchmarks Grants, a new program committing $3M in grants to fund new open source benchmarks advancing agentic AI. We’re partnering up with @HuggingFace
, @togethercompute
, @PrimeIntellect
, Factory HQ, @harborframework
, and @PyTorch to -
General Agentic Memory Via Deep Research in AI Systems
By
–
General Agentic Memory Via Deep Research https://
bit.ly/49urPcE
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Aletheia: AI Math Research Agent Solves Erdős Open Problems
By
–
Yesterday we just shared Aletheia, our math research agent that enables autonomous math research and solving Erdos open problems. Yes, this Gemini 3 deep think was *the* deep think. It's launched! nitter.net/YiTayML/status/2021750… Yi Tay (@YiTayML) Introducing Aletheia, a math research agent powered by an advanced version of Gemini Deep Think that produces publishable math research (two papers, one completely automatic and another with human-AI collaboration) and solved multiple open Erdős problems. 😀🔥 Paper link below! 👇 — https://nitter.net/YiTayML/status/2021750645666328779#m
-
A2A: Agent2Agent Protocol Course for Multi-Agent Systems
By
–
New course: A2A: The Agent2Agent Protocol, built with @googlecloudtech and @IBMResearch, and taught by Holt Skinner, @ivnardini, and Sandi Besen.
— Andrew Ng (@AndrewYNg) 12 février 2026
Connecting agents built with different frameworks usually requires extensive custom integration. This short course teaches you A2A,… pic.twitter.com/lgEXdqSis9New course: A2A: The Agent2Agent Protocol, built with @googlecloudtech and @IBMResearch, and taught by Holt Skinner, @ivnardini, and Sandi Besen. Connecting agents built with different frameworks usually requires extensive custom integration. This short course teaches you A2A, the open protocol standardizing how agents discover each other and communicate. Since IBM’s ACP (Agent Communication Protocol) joined forces with A2A, A2A has emerged as the industry standard. In this course, you'll build a healthcare multi-agent system where agents built with different frameworks, such as Google ADK (Agent Development Kit) and LangGraph, collaborate through A2A. You'll wrap each agent as an A2A server, build A2A clients to connect to them, and orchestrate them into sequential and hierarchical workflows. Skills you'll gain: – Expose agents from different frameworks as A2A servers to make them discoverable and interoperable – Chain A2A agents sequentially using ADK, where one agent's output feeds into the next – Connect A2A agents to external data sources using MCP (Model Context Protocol) – Deploy A2A agents using Agent Stack, IBM's open-source infrastructure Join and learn the protocol standardizing agent collaboration! deeplearning.ai/short-course…
→ View original post on X — @andrewyng, 2026-02-12 16:30 UTC