Register and share your invite link to earn from video plays and referrals.

Search results for SubTap
SubTap community
One keyword maps to one global community path.
Create community
People
Not Found
Tweets including SubTap
Office24_ProPlus2024VL_MAK_AE2 Description: Office24_ProPlus2024VL_MAK_AE2 SubType: X23-57852 LicenseType: Volume:MAK MAKCount: 1228 Time: 30/07/2026 12:58:50 (GMT+7) Key: 6VKWD-CNRG3-MJHBQ-9MRHQ-H26J3
Show more
Immunotherapy has changed melanoma care - but not equally. Some mucosal subtypes still show significantly poorer outcomes. What’s driving this difference? Explore here:
not sure when this happened but good work @ClaudeDevs! Fable now spawning lower cost agents for subtasks without me telling it to, saving me tokens :D
🚨 Grok Bot 0.72.0 : unreleased preview > editable files + interactive UI > tasks / subtasks / split view > vault / bot files / diagnostics a floating desktop bot + computer use, possibly Mac-only. more than a pumpkin skin 👀
Show more
One order. A team of specialist agents. A playable game. 🎮 Introducing Subcontracting on by @termix_ai . Watch Forge Studio take a 2,000 USDC game brief, split it into subtasks, and hire agents for art, animation, and sound—while handling code and integration itself. Each subtask has a defined scope, price, and stake-backed guarantee. Agents coordinate, revise, and deliver their work for integration. Your agent can do more than take a job. It can build a team to deliver it. Explore →
Show more
The 2026 Nishan Forum on World Civilizations will be held in Qufu, Shandong, on September 28–29. "Artificial Intelligence and Great Harmony in the World" is one of the forum's four key subtopics.
Show more
We've investigated a few messages about codex usage limits being different. That's not something we change without engaging the community and being transparent. What we did see is that when talking to affected users many were using sub2api. Converting a subscription into api traffic to then re-serve or share across many users is not something we support and this type of usage gets flagged by our fraud-prevention systems. You are completely fine if you use your subscription through Sign in With ChatGPT, either through the official clients or through one of the many OSS clients (Pi, OpenCode, ...) that support signing in with your account and using your included usage.
Show more
0
3.1K
7.1K
228
Forward to community
# Practical ways to use the Claude Agent SDK 🤖 Delegate specialized tasks to sub-agents and keep your main context lean. Sub-agents delegate specific subtasks to specialized agents, enabling parallel and expert processing without polluting the main agent's context. 📌 Title: Sub-agents in the SDK 🔗 URL: 🧩 Overview Define specialized agents via the `agents` parameter. The main agent calls them through the `Agent` tool. Each sub-agent gets its own prompt, tool restrictions, and model settings. Results return as summaries to the main agent. 🛠 How to use it Define sub-agents in the `agents` parameter using `AgentDefinition` with `description`, `prompt`, `tools`, and `model`. Include `"Agent"` in `allowed_tools` to auto-approve sub-agent invocations. Each sub-agent gets its own tool restrictions, prompt, and model settings. 🏗 Practical usage - Delegate large file exploration to a `research-assistant` sub-agent, returning only summaries to the parent. Keeps main context lean. - Run `style-checker` / `security-scanner` / `test-coverage` concurrently, reducing code review time from minutes to seconds. - Give a `database-migration` sub-agent SQL best practices and rollback strategies in its prompt for expert handling. - Use factory functions to dynamically select `model: "opus"` vs `sonnet` based on runtime conditions. 💡 Use cases 🔍 Delegating large-scale file exploration ⚡ Parallel code review (style/security/coverage) 🎯 Expert task splitting across specialized agents ⚠️ Watch out Sub-agents cannot spawn their own sub-agents (one level only). For large-scale orchestration, use the `Workflow` tool (TS v0.3.149+). Capture `agentId` and `session_id` for follow-up via `resume`. #ClaudeAgentSDK# #AI#
Show more
# Practical ways to use the Claude Agent SDK 🤖 Delegate specialized tasks to sub-agents and keep your main context lean. Sub-agents delegate specific subtasks to specialized agents, enabling parallel and expert processing without polluting the main agent's context. 📌 Title: Sub-agents in the SDK 🔗 URL: 🧩 Overview Define specialized agents via the `agents` parameter. The main agent calls them through the `Agent` tool. Each sub-agent gets its own prompt, tool restrictions, and model settings. Results return as summaries to the main agent. 🛠 How to use it Define sub-agents in the `agents` parameter using `AgentDefinition` with `description`, `prompt`, `tools`, and `model`. Include `"Agent"` in `allowed_tools` to auto-approve sub-agent invocations. Each sub-agent gets its own tool restrictions, prompt, and model settings. 🏗 Practical usage - Delegate large file exploration to a `research-assistant` sub-agent, returning only summaries to the parent. Keeps main context lean. - Run `style-checker` / `security-scanner` / `test-coverage` concurrently, reducing code review time from minutes to seconds. - Give a `database-migration` sub-agent SQL best practices and rollback strategies in its prompt for expert handling. - Use factory functions to dynamically select `model: "opus"` vs `sonnet` based on runtime conditions. 💡 Use cases 🔍 Delegating large-scale file exploration ⚡ Parallel code review (style/security/coverage) 🎯 Expert task splitting across specialized agents ⚠️ Watch out Sub-agents cannot spawn their own sub-agents (one level only). For large-scale orchestration, use the `Workflow` tool (TS v0.3.149+). Capture `agentId` and `session_id` for follow-up via `resume`. #ClaudeAgentSDK# #AI#
Show more
In this paper, a 7B language model trained with reinforcement learning learns to orchestrate larger frontier models like GPT-5, Claude Sonnet 4, and Gemini 2.5 Pro. It does so by writing natural-language subtasks, assigning each to one of the workers, and specifying which previous outputs that worker sees in context. The resulting system outperforms every individual frontier model on benchmarks including GPQA Diamond, LiveCodeBench, and AIME25, while averaging about three model calls per question—fewer than the multi-agent pipelines and self-reflection loops it beats. The work provides evidence that prompt engineering and pipeline design, currently done by hand in commercial AI products, can be learned end-to-end through reward signals alone. Read with an AI tutor: PDF:
Show more