Amp puts AI agents to work beyond code with OpenAI models
See how Amp pushes the frontier of what agents can do with GPT-6 Astra, Ultrafast, GPT-Live-1, and Sign in with ChatGPT.
Source: OpenAI Blog
Top Stories
The World Won't Wait: Evaluating and Teaching Agents Under a Live Clock
arXiv:2610.20665v1 Announce Type: new Abstract: Large language model (LLM) agents can solve complex interactive tasks, yet reasoning and tool calls take time. In continuously changing environments, an otherwise correct action may arrive too late. We introduce RealtimeBench, with 180 tasks across six game types, to evaluate agents while games continue running during inference. Paired evaluations show that GPT-6.1-sol outperforms the faster Jev when games are paused, but falls behind when they keep running. We propose Two-Timescale Offline Recursive Self-Improvement (TORSI): a slow teacher studies failures and tests corrections in paused games between attempts, then writes reusable instructions for a fast student. The student acts without teacher calls during gameplay, and validation scores determine which updates are adopted. Two rounds raise Jev's average test score from 13.51 to 24.19 on a 0--100 progress scale, improving all six game types. The instructions also improve average scores for three other models without retuning....
How Third Moment Research runs 10,000 agents for 36+ hours
With GPT-6 Astra and GPT-6.1 Sol, Codex, and Daybreak for cybersecurity, this AI lab builds agents that focus for days and improve with use.
What I Learned Building Multiple MCP Servers for Local LLMs (Qwen3-8B): Tool Granularity, Latency Traps, and Dogfooding
Recently, I have been building a local data analysis stack pairing LM Studio (Qwen3-8B) with custom Model Context Protocol (MCP) servers to query and cross-analyze over 180 normalized Japanese government and corporate datasets. At first, I fell into the classic developer temptation: "What if I build an MCP tool for everything—web scraping, stock prices, climate data, random correlation discovery, and multi-platform publishing?" However, running multiple MCP servers against a local 8B model quickly exposed real-world bottlenecks that you rarely notice when using frontier cloud models. Here are the 5 biggest engineering lessons I learned from building and open-sourcing our MCP servers (japan-data-mcp and correlation-discovery-mcp)—including an unexpected plot twist at the end. Enabling every cool MCP server you find is the fastest way to ruin your local LLM experience. Every time you send a message, the MCP client injects the full JSON Schema definitions of all currently enabled tools into the...
Meta Ships Muse Wonder, Jev Raises $870M 24 Days After Launch, and Anthropic Cuts Haiku 90%: The Top Takeaways From This Week’s 20VC x SaaStr
Pro rata goes to Delaware, Nvidia circles Reflection, a record 42 decacorns, and why the B2B apocalypse never ended for anyone under $1B in ARR A nuclear startup took its earliest institutional backer to court over a spring-back clause. Meta put its first model at the frontier. A 20-person team raised $870 million less than... Continue Reading
Sullivan & Cromwell brings legal expertise into agreement review
In collaboration with OpenAI, Sullivan & Cromwell developed Agreement Analyzer, an AI tool for identifying issues in a draft agreement.
Quick Bytes
SentinelOne cuts malware analysis from weeks to hours — OpenAI Blog
How Block is building AI-powered security with OpenAI technology — OpenAI Blog
Meta launches an open-weight AI model that runs on Macs — TechCrunch AI