Grok 자동화, 에이전트 신뢰성 측정, Transformer 구조 학습과 AI 제품 확장

Elon Musk

@elonmusk

14일 전

Try Grok @Bot

Maybe one day Grok @bot can run the factory end-to-end.

What a fascinating paper on AI agents. A lot of the issues we see with AI agents today revolve around wrong assumptions the LLMs make. This leads to problems like hallucination, cost inefficiencies, unreliable tool calls and much more. I think if we can solve this problem, even current LLMs would significantly improve in terms of performance and efficiency. The problem is that context acquisition is treated as afterthought, but it shouldn't be that way. Users tend to leave out constraints when prompting. So the agent agent needs to guess the default, or spend tokens on a clarifying question, a retrieval call, a tool call, or a prompt trial. This new work gives this problem an objective function. Context acquisition becomes active inference over a latent task state. An inner step updates beliefs, and an outer step picks the next context action, task action, or stop action to minimize expected free energy under cost. In deterministic settings the epistemic term reduces to expected information gain, optionally normalized by token cost. That is directly implementable today as a scoring rule. They coin it as Optimal Question Asking, with exact posteriors and a dynamic programming oracle, then benchmark frontier models on binary and multiway tasks from 25 to 300 candidates. So you can measure the gap between your agent and the true optimum. Paper: https:// arxiv.org/abs/2608.19202 Track more trending AI papers in our academy: https:// academy.dair.ai

Banger paper from Microsoft. It's on agent reliability in real business workflows. (bookmark it) Thinkingbox is a sandbox with isolated MCP-compatible tool sessions, plus a benchmark of 507 policy-conditioned workflows across retail, hospitality, auto insurance, neobank IT, and consulting support. Every attempt is graded on the backend state the agent leaves behind. Executable checks accept valid trajectories and reject wrong, missing, or extra effects, so collateral damage counts against you. The strongest model reaches 65.36% pass@1 and 25.25% pass^20. Many failed trials terminate cleanly with valid state-changing tool calls. Watching the response or the tool call tells you very little about whether the task actually completed. Paper: https:// arxiv.org/abs/2608.19741 Track more trending AI papers in our academy: https:// academy.dair.ai

Working with multiple AI agents shouldn’t mean rebuilding the same setup every time. Omnigent is Databricks’ open-source meta-harness that gives agents a shared layer for orchestration, control, and collaboration. Switch agents without losing context, route tasks intelligently, set contextual policies and spend controls, and add human approval where it matters. @YoussefMrini and Quentin Ambard sit down with Databricks co-founder and CTO @matei_zaharia to show how it all comes together. https:// youtube.com/watch?v=sk6HBd mVmL8 …

Claude Code 2.1.240 has been released. 1 CLI change Highlights: • Bug fixes and reliability improvements to the CLI to reduce crashes and improve error messages • CLI fixes reduce crashes and improve command consistency, leading to fewer interruptions and steadier results All details in thread ↓

Transformer by hand ~ 6 steps walkthrough below Studying the Transformer architecture is like opening up the engine hood of your car. So many unknown parts: embeddings, positional encoding, attention weighting, self-attention, cross-attention, multi-head attention, layer norm, skip connections, softmax, linear, Nx, shifted right, query, key, value, masking. But which of those actually make the car run? I think at the core, there are two most essential components: Attention weighting and the feed-forward network. Everything else is an enhancement to make it run faster and longer, which is how we got from a car to a truck, and to the word "large" in large language model. So I drew and calculated those two parts entirely by hand. Goal: push five features through one transformer block, filling in every cell yourself. 1. Given Five positions of input features, arriving from the previous block. 2. Attention matrix Let us feed all five features to a query-key module (QK) and read back an attention weight matrix, A. The details of that module are a post of their own. 3. Attention weighting We multiply the input features by A to get the attention weighted features, Z. Still five positions. The effect is to combine features *across positions*, horizontally: X1 becomes X1 + X2, X2 becomes X2 + X3, and so on. 4. First layer Let us feed all five weighted features into the first layer of the FFN. Multiply by the weights and biases. This time the combining happens *across feature dimensions*, vertically, and each feature grows from 3 numbers to 4. Note that every position goes through the same weight matrix. That is what "position-wise" means. 5. ReLU We cross out the negatives. They become zeros. 6. Second layer Let us bring it back down: 4 dimensions to 3. The output feeds the next block, which has a completely separate set of parameters, and the whole thing runs again. You have just calculated a transformer block by hand. The takeaway: the two parts are doing two different jobs, and neither one alone is enough. Attention mixes across positions, so a feature can see its neighbours. The FFN mixes across feature dimensions, so each position can think about itself. Horizontal, then vertical. Then that pattern repeats N times, each block with its own separate set of weights. That is the Nx from the list up top, and that is what makes the transformer run. Save this post! #AIbyHand #Transformers #DeepLearning

Trung Phan

@TrungTPhan

14일 전

Chinese humanoid robot by smartphone maker Honor (“Lightning”) ran 100m in 9.32 seconds (Usain Bolt’s record is 9.58 seconds). Perhaps more impressively: it crashed into a safety wall without having its waist implode with sparks flying off.

A new study finds leading AI labs have few publicly documented plans for containing rogue models, raising questions about preparedness as AI systems increasingly demonstrate unexpected and potentially dangerous behavior.

OpenAI is calling for California to strengthen SB 53, an AI safety bill that the company previously opposed.

Cristóbal Valenzuela

@c_valenzuelab

14일 전

Runway is officially coming to LATAM. Last month, we visited our customers in Brazil, and now it’s Chile We’re meeting with some of the most important companies and customers in Chile and also with @GobiernodeChile . We also have a few community events, so if you’re there, make sure to join us. LATAM is becoming an incredibly important user base for Runway. We’re already in Japan, France, and the UK, and we’ll continue our global expansion to make sure Runway reaches every corner of the world. Dos chilenos de vuelta a su país @matamalaortiz

Google’s Pixel 11 Pro XL brings snappier cameras and genuinely useful AI features like Rambler, but its iterative upgrades may not be enough to tempt recent Pixel owners.