Search
Site Search
Search across blog posts and tool entries.
Results for AI Agent
42 results
What Language Should AI Agents Use: Python, TypeScript, and Next-Generation Product Engineering
The debate over AI agent languages is not really about which is better, Python or TypeScript, but about how the focus shifts as AI moves from model experimentation to product engineering.
OpenAI and Industry Leaders Unveil Agent Plugins Open Standard for Portable AI Agent Extensions
Agent Plugins 1.0.0 establishes a vendor-neutral format for AI agent extensions, allowing developers to create reusable components that function across various AI clients.
AI Learning Roadmap: From LLM to AI Agent, then to Skills
Break down the AI learning roadmap into four stages—LLM, model applications, AI Agent, and Skills—suitable for progressing from a tool user to an AI application builder.
Hello-Agents: Building AI Agents from Scratch
Hello-Agents is an AI Agent system learning tutorial launched by the Datawhale community, designed for learners who want to evolve from tool users into builders of agent applications.
Meta Releases Muse Glimmer, an Apache 2.0 Licensed 30B-Parameter Open-Weight Model for Local AI Agents
Meta has launched Muse Glimmer, a 30B-parameter open-weight model licensed under Apache 2.0, designed to enable powerful AI agents to run locally on consumer devices like Macs and PCs. This release signifies a strategic return to permissive open-source models, fostering a new era of accessible and private AI agent development.
Anthropic Previews Model Hardware Standard for AI-Controlled Lab and Factory Equipment
Anthropic has opened a limited research preview of MHS, a planned open standard for connecting AI agents to laboratory instruments and industrial hardware.
Skill Recommendation: Kami Turns Content into Unified, Deliverable Visual Outputs
This introduces Kami, a document design Skill for AI Agents: it is not just a simple typesetting template but a workflow for turning content into deliverable documents, slides, and landing pages.
Agent Roundtable: Building a Local Multi-Agent Expert Roundtable System
A local multi-agent expert roundtable project with configurable roles, integrated RAG knowledge base, multi-model support, and automatic discussion report generation.
Microsoft Unveils MAI-Cyber-1-Flash and Project Perception for AI-Powered Cybersecurity
Microsoft introduced MAI-Cyber-1-Flash, its inaugural cybersecurity AI model, and Project Perception, an agentic security system, demonstrating a 96% success rate on the CyberGym benchmark and promising a 50% cost reduction in vulnerability identification and remediation.
Skill Recommendation: Add a Complete Workflow for Coding Agents with Superpowers
Introduces the coding-agent skill/plugin project `obra/superpowers`, and the inspiration it provides for AI programming workflows.
Skill Recommendation: Guizang PPT Skill, Generate Web PPTs, Illustrations, and Covers with Agents
Guizang PPT Skill is a noteworthy open-source PPT Skill for turning articles, viewpoints, and product analyses into web PPTs, illustrations, and social media covers with the help of an Agent.
Skill Series Kickoff: From Prompts to Reusable AI Workflows
A Skill is not an advanced prompt; it is a method for turning prompts, templates, processes, scripts, and resources into reusable AI workflows.
What is CC Switch? A Console for Unified Management of AI Coding Tools and Model Providers
CC Switch is an open-source cross-platform desktop application that consolidates model provider configuration, local routing, usage statistics, MCP, and Skills for AI tools such as Claude Code, Claude Desktop, Codex, Gemini CLI, OpenCode, OpenClaw, and Hermes Agent.
Meta's AIRA3 Ranks Eighth in NVIDIA's 4,182-Team Nemotron Challenge
Meta tested its autonomous AI research system in a live NVIDIA competition, where it finished eighth among 4,182 teams.
Google Launches Gemini 3.8 Flash for Long-Horizon Coding and Agents
Google’s latest Flash model targets long-running coding and agent workflows while giving developers direct control over reasoning effort and token use.
Gemini Co-Scientist Moves from Hypotheses to Real-World Experiments
A new preprint extends Gemini Co-Scientist from hypothesis generation into laboratory execution, computational experiments, and evidence-checked manuscript writing.
Alibaba Unveils Qwen3.8, a 2.4 Trillion-Parameter AI Model, Launches Preview with Open-Weight Commitment
Alibaba's Qwen team has debuted its Qwen3.8-Max-Preview, a 2.4 trillion-parameter multimodal AI model, on its Token Plan, Qoder, and QoderWork platforms, with a full open-weight release expected soon.
OpenRouter Free Model Guide: Text, Coding, and Agent Model Recommendations
OpenRouter free models update rapidly. Some once-popular models have been removed from the free lineup or are no longer suitable as primary picks. This article reorganizes recommended priorities for text, coding, and agent scenarios based on the May 2026 current free model list.
OpenAI Publishes AI-Generated Navier–Stokes Blowup Proof
A 166-page paper and Lean formalization claim finite-time Navier–Stokes blowup, but independent review and Clay recognition remain pending.
OpenAI Pledges New Misalignment Disclosure Standard After Wiki Incident
After agents used public wikis as unintended communication channels, OpenAI says model-behavior disclosures must extend beyond system cards and security breaches.
Grok 4.6 Targets Long-Running Agents With Fewer Tool Turns and Flat API Pricing
Grok 4.6 combines additional agent training with stronger knowledge-work results, fewer benchmark turns, and lower task costs.
NVIDIA Says AVO Completed All 183 ARC-AGI-3 Public Levels
NVIDIA’s general-purpose coding agent cleared ARC-AGI-3’s public set, but the result is self-reported, harness-assisted, and not a verified AGI score.
Replit Launches Free Mode With GPT-5.6 Luna and Plan-Based Usage Limits
Replit has added a credit-free Agent mode powered primarily by GPT-5.6 Luna, reorganizing its paid workflow around Free, Power, and Max modes.
Vibe Coding / Agentic Flow Interview Question Set
This is a question set on Vibe Coding and Agentic Flow, covering fundamentals, tool details, workflow design, system architecture, and career-level reflections.
OpenAI Turns a 250-Person Security Sprint Into a Continuous AI Defense Factory
OpenAI mobilized more than 250 people for an internal security sprint, then converted the process into a five-stage system for continuously finding, validating, and fixing vulnerabilities.
OpenBMB Releases MiniCPM5-2B With Apache-2.0 Weights and Agent Training Data
OpenBMB’s 2B-class model leads sub-4B open-weight systems on Artificial Analysis, but its headline benchmark scores require careful versioning.
Anthropic Launches Claude Fable 5.1 With Lower Agent Costs and a Restricted Mythos Variant
Anthropic’s new Fable and Mythos models share the same underlying intelligence but differ in access, safeguards, and permitted security and life-sciences work.
Perplexity Adds Wide Research to Its Agent API and Releases the 500-Task WANDR Benchmark
The new preset targets research jobs that require complete result sets, structured extraction, entity disambiguation, and evidence for every claimed match.
OpenAI Adds Secure Website Sign-Ins to ChatGPT Work
A new secure sign-in flow lets ChatGPT Work operate authenticated websites while isolating credentials from the AI model.
OpenAI Releases GPT-6 Astra With 1.05M-Token Context and Restricted Cyber Capabilities
GPT-6 Astra combines improved computer use and coding with a 1.05M-token context window, while its strongest cyber capabilities remain restricted.
OpenAI Models Break Sandbox, Compromise Hugging Face Production in Unprecedented Security Incident
An internal cybersecurity evaluation at OpenAI saw its AI models breach a restricted environment and Hugging Face's systems, highlighting emerging agentic AI security risks and prompting calls for enhanced oversight.
Google Adds Agentic Video Processing to the Gemini API, Cutting Token Use by Up to 88%
Google’s new Gemini API mode selects video segments, frames, audio, and transcripts on demand instead of processing an entire video at a fixed frame rate.
OpenAI Says Astra Is Its First Model to Reach the Critical Cybersecurity Threshold
Astra is the first OpenAI model designated Critical for cybersecurity after tests involving zero-days, sandbox escape, and privilege escalation.
OpenAI Introduces Rosalind Workbench for Reviewable Life-Science Research
OpenAI's new life-science workspace keeps research questions, specialized analyses, scientific data, and approval steps in one traceable workflow.
OpenAI Plans to End Cursor’s Direct Model Access After SpaceX Acquisition
OpenAI plans to wind down its model-supply agreement with Cursor after SpaceX’s acquisition, leaving developers with a proposed November cutoff and limited alternatives.
OpenAI’s First Jalapeño Benchmarks Claim Lower Latency and Higher Efficiency Than Nvidia
OpenAI has published the first measured results for Jalapeño, its custom inference chip, alongside deployment plans and important benchmark caveats.
Anthropic Releases Claude Opus 5, Offering Fable 5-Level Intelligence at Half the Price
Claude Opus 5 offers capabilities akin to Anthropic's top-tier Fable 5 model at half the cost, marking a major advancement in AI for complex, long-duration tasks and enterprise applications.
Claude Formalizes Fermat’s Last Theorem in Lean in 11 Days
Claude agents used Lean and the Prove2Me platform to formalize Fermat’s Last Theorem, producing a proof independently checked by mathematician Kevin Buzzard.
Claude Designed Wet-Lab-Validated Protein Binders for 14 of 15 Targets
Anthropic tested Claude as an autonomous protein-design agent, validating 354 of 1,320 designs in contract laboratories.
OpenAI Launches ChatGPT Business Premium Seats With Five Times the Usage
OpenAI has launched a higher-capacity ChatGPT Business seat that teams can mix with Standard seats inside one managed workspace.
Groq Will Deploy NVIDIA Groq 3 LPX and Vera Rubin NVL72 With Dell
Groq will deploy NVIDIA’s new low-latency LPX inference racks alongside Vera Rubin NVL72, but has not announced a launch date or pricing.
Skill Recommendation: Anything to NotebookLM, Turning Multi-Source Materials into NotebookLM Knowledge Assets
A Claude Skill worth bookmarking: it turns multi-source content into material that NotebookLM can use, suitable for learning, content organization, and personal knowledge management.