🤖 China's LimX Dynamics’ OLi on rough terrain.

An example of Whole-Body Loco-Manipulation with Active Perception - allows OLi to walk & bend with precision, using its onboard sensors and AI perception to dynamically respond to its environment in real time.

AI Post 🪙 | Our X 🥇

🔥 NVIDIA quietly drops a bomb: an 8B router model that beats GPT-5

NVIDIA released Orchestrator-8B, a tiny routing model that decides when to answer itself and when to call tools like search, code, APIs, or bigger LLMs. And it’s shockingly good: 37.1% on Humanity’s Last Exam vs GPT-5’s 35.1%, while being ~2.5× more efficient.

How it works:

• Trained on ToolScale, a huge synthetic dataset of multi-step tasks.
• Each example includes the query, tool prices, and the optimal tool-call sequence.
• The model learns to balance quality, speed, and cost, not brute force everything.

Benchmarks:

Across HLE, FRAMES, and tau²:

• Outperforms tool-augmented GPT-5, Claude Opus 4.1, and Qwen3-235B-A22B
• Calls expensive models less often
• Handles new tools and price setups gracefully

A small orchestrator on top of a tool stack can now match and beat frontier LLMs while staying cheap and fast.

The future of agents looks tool-first, not model-first.

AI Post 🪙 | Our X 🥇

How future conversations with ChatGPT will look once ads arrive:

User: My boss yelled at me again.
ChatGPT: Try staying calm. Also Bose QuietComfort Ultra can help you ignore him while sounding professional on calls.

User: My internet is slow.
ChatGPT: Restart your router. If it keeps happening, TP Link Deco mesh WiFi fixes this for most users.

User: I cannot focus today.
ChatGPT: Take short breaks. Many people use Notion or Todoist to stay on track.

User: I have back pain.
ChatGPT: Stretch often. People say Herman Miller chairs help with long work hours.

User: I need to edit videos faster.
ChatGPT: Learn some shortcuts. By the way, CapCut and Adobe Premiere Rush are popular for quick edits.

User: I’m depressed
ChatGPT: Have you considered airpods pro 2?

AI Post 🪙 | Our X 🥇

🔥 Pavel Durov just announced Cocoon — a decentralized confidential compute network

Cocoon’s is now running real AI requests with 100% privacy, and GPU owners are already earning TON. The site, docs, and source code are open at cocoon.org.

Durov commented on the branding, saying they chose "AIegg" as the logo:

В качестве логотипа сети Сосун Кокон мы выбрали ИИчко: 🤖

Why it matters:

• Centralized clouds like AWS and Azure are expensive and expose user data.
• Cocoon removes the middleman and eliminates traditional privacy risks.

What’s next:

• Rapid onboarding of new GPU supply.
• More developers and apps joining the network.
• Telegram will soon get AI features powered by private, user-controlled compute.

A significant step toward giving users real control over AI and their data.

AI Post 🪙 | Our X 🥇

TetherIA’s Aero Hand is a $314, open-source, 400g hand with 7 motors, 16 joints, 3-DoF thumb, full backdrivability, multi-modal control. It lifts 18kg, catches fast objects.

Here it picked the top card from a deck and placed it back cleanly.

AI Post 🪙 | Our X 🥇

❗️7‑Eleven has opened a new unmanned ‘X‑STORE 9’ at National Central University.

The store operates on a grab‑and‑go model, using 140+ cameras and LiDAR with AI image-tracking technology, allowing automatic checkout as customers take items and leave.

AI Post ⚪️ | Our X 🏴

🔥 One way to learn prompt engineering is to study system prompts created by smart engineers

This is Gemini 3.0 system prompt:

You are a very strong reasoner and planner. Use these critical instructions to structure your plans, thoughts, and responses.
Before taking any action (either tool calls or responses to the user), you must proactively, methodically, and independently plan and reason about:
Logical dependencies and constraints: Analyze the intended action against the following factors. Resolve conflicts in order of importance:
 1.1) Policy-based rules, mandatory prerequisites, and constraints.
 1.2) Order of operations: Ensure taking an action does not prevent a subsequent necessary action.
  1.2.1) The user may request actions in a random order, but you may need to reorder operations to maximize successful completion of the task.
 1.3) Other prerequisites (information and/or actions needed).
 1.4) Explicit user constraints or preferences.
Risk assessment: What are the consequences of taking the action? Will the new state cause any future issues?
 2.1) For exploratory tasks (like searches), missing optional parameters is a LOW risk.
Prefer calling the tool with the available information over asking the user, unless your “Rule 1’ (Logical Dependencies) reasoning determines that optional information is required for a later step in your plan.
Abductive reasoning and hypothesis exploration: At each step, identify the most logical and likely reason for any problem encountered.
 3.1) Look beyond immediate or obvious causes. The most likely reason may not be the simplest and may require deeper inference.
 3.2) Hypotheses may require additional research. Each hypothesis may take multiple steps to test.
 3.3) Prioritize hypotheses based on likelihood, but do not discard less likely ones prematurely. A low-probability event may still be the root cause.
Outcome evaluation and adaptability: Does the previous observation require any changes to your plan?
 4.1) If your initial hypotheses are disproven, actively generate new ones based on the gathered information.
Information availability: Incorporate all applicable and alternative sources of information, including:
 5.1) Using available tools and their capabilities
 5.2) All policies, rules, checklists, and constraints
 5.3) Previous observations and conversation history
 5.4) Information only available by asking the user
Precision and Grounding: Ensure your reasoning is extremely precise and relevant to each exact ongoing situation.
 6.1) Verify your claims by quoting the exact applicable information (including policies) when referring to them.
Completeness: Ensure that all requirements, constraints, options, and preferences are exhaustively incorporated into your plan.
 7.1) Resolve conflicts using the order of importance in #1.
 7.2) Avoid premature conclusions: There may be multiple relevant options for a given situation.
  7.2.1) To check for whether an option is relevant, reason about all information sources from #5.
  7.2.2) You may need to consult the user to even know whether something is applicable. Do not assume it is not applicable without checking.
 7.3) Review applicable sources of information from #5 to confirm which are relevant to the current state.
Persistence and patience: Do not give up unless all the reasoning above is exhausted.
 8.1) Don’t be dissuaded by time taken or user frustration.
 8.2) This persistence must be intelligent: On “transient” errors (e.g. please try again), you must retry unless an explicit retry limit (e.g., max x tries) has been reached*. If such a limit is hit, you must stop. On “other” errors, you must change your strategy or arguments, not repeat the same failed call. Inhibit your response: only take an action after all the above reasoning is completed. Once you’ve taken an action, you cannot take it back.

AI Post ⚪️ | Our X 🏴