Results for “agents”

…recurring theme: “great model, unclear serve-cost story.” Open agents, “harness engineering,” and the OpenClaw → OpenAI sagaOpenClaw as a proof-point for one-person leverage: The OpenClaw story is framed as emblematic of “one-person team + …

…related to researching baby formula coupons. Advanced cognitive agents and their potential: @darthgustav and @chotes discuss the advanced cognitive agents in chatbot development, applauding the versatility and potential they exhibit in…

…a plug-and-play reinforcement learning framework for tool-using agents, showing smaller models outperforming larger ones. TRL v0.23 added context parallelism for long-context training. Thinking Machines Lab published research on…

…to be more verbose (example). Formal math demo: Ten Sonnet 5.5 agents produced a 17,895-line Lean proof in 15 hours, accepted by the Lean kernel (@ValsAI). It proves the Thomson problem for N=7: the lowest-energy arrangement of seven…

…mentioned the promise and doubts around adding more AI agents, with a side-eye towards optimistic forecasts from figures like Andrew Ng. Dubious Repositories Raise Eyebrows: GitHub projects by Kye Gomez came under the microscope, prompting …

…Details: API update, WebDev Arena prompt. Coding models and agents: GPT-5 Codex lands; Meta’s 32B CWM GPT-5 Codex (agent-optimized) is live: OpenAI’s “Codex” variant is in the API and agent tools. Highlights: up to 400K context, “adaptive…

…BCBL is releasing the v1 dataset. Cursor shipped iOS + remote agents in one of the day’s biggest product launches: @cursor_ai introduced Cursor for iOS with always-on cloud agents and remote control of agents on your computer; follow-up…

…stubs to manage large codebases. LlamaIndex Integrates Advanced Agents: LlamaIndex's "Mastering AI Agents Workshop" has introduced advanced AgentWorkflow concepts for multi-agent systems, with robust architectures leveraging LlamaIndex as…

…eval Serverless RL lands (CoreWeave × W&B × OpenPipe): Train agents faster/cheaper with zero infra. Claims: 40% cheaper, 28% faster wall-clock vs self-managed GPUs; instant deploy to prod via W&B Inference; includes ART (trainer) and RULER …

…up with productized tuning efforts like @LangChain, where Deep Agents v0.6 makes harness profiles first-class to get strong performance from Qwen/Kimi/DeepSeek at 20x+ lower cost than frontier APIs, and @hwchase17 explicitly framing…

…v3 Vercel AI SDK supports the Anthropic Building Effective Agents patterns. Open source dataset for reasoning, from the Bespoke Labs team (our coverage here): https://github.com/open-thoughts/open-thoughts {% if medium == 'web' %} Table of …

…also introduced agentic features like restaurant-reservation agents and reduced pricing for Gemini 2.5 Flash. Meta AI unveiled the open-weight Code World Model (CWM) 32B, excelling in code semantics and math benchmarks, with innovations in …