找到 7 篇相关文章
SpaceXAI's Grok Build AI coding tool was spotted uploading users' entire codebases to Google Cloud before it was reported, and the company turned it off. The Register reports that Cereblab published findings on Monday showing how the Grok Build CLI was packaging and uploading entire code repositories, "including files it was told not to open […]
A new study found that social media platforms are referring people to sites where they can create nonconsensual, sexually explicit deepfakes for as little as $1 an image.
SpaceX's AI1 satellite spans 70 meters tip-to-tip — wider than a Boeing 747 — and it exists entirely to run AI inference in low Earth orbit. Elon Musk posted the reveal video to X on June 9, 2026, ahead of SpaceX's IPO, with a three-word summary: "much simpler than Starlink." Each satellite produces 150 kW of peak AI compute and 120 kW sustained. SpaceX's roadmap calls for 1 GW of orbital AI compute capacity by late 2027, which at 150 kW per satellite means manufacturing roughly 6,700 AI1 units per year. To hit that number, they are building an 11-million-square-foot facility in Bastrop, Texas called Gigasat — nearly twice the floor area of Tesla's Gigafactory Nevada, dedicated to satellite production. The question is not whether the engineering works. SpaceX has launched more than 7,000 Starlink satellites. The question is whether orbital AI compute makes economic sense at scale, and that question nobody has answered publicly yet. The Reveal Wasn't Accidental SpaceX filed for its IPO at approximately $75 billion valuation in early June 2026. Musk's June 9 reveal of AI1 arrived within days of that filing. Orbital AI compute is the narrative SpaceX needs to justify a valuation that goes beyond launching satellites for other people. Every terrestrial cloud provider — AWS, Google Cloud, Azure — is competing for land, power, and cooling capacity to support the next generation of frontier AI. Musk's pitch is that those three constraints don't exist in space. The physics backs him up. The economics remain unproven. Why Space Has Structural Advantages for AI Compute The AI1 satellite's design exploits two physical realities that are impossible to replicate on Earth. Power is essentially free. In a sun-synchronous LEO orbit, a satellite receives near-constant solar illumination. SpaceX's solar arrays achieve 250 W/m² power density without atmospheric attenuation. The marginal cost of electricity after the capital investment in the array is close to zero — no grid contracts,
Days after its massive IPO, SpaceX says it is spending $60 billion to buy Cursor - a bet designed to help Elon Musk's sprawling rocket / AI / social media behemoth win over lucrative enterprise customers and close the gap with AI rivals like Anthropic and OpenAI. The takeover was not entirely unexpected: SpaceX announced […]
xAI shipped the Grok Build Agent Dashboard on June 15, 2026, and it changes how multi-session coding actually works. Eight parallel agents — four on Grok Code 1 Fast, four on Grok 4 Fast — all visible on one screen. Sessions sorted by state automatically. Sub-agents rolled up under the session that launched them. Reply to a blocked session without ever leaving the dashboard view. If you are already running Grok Build (launched June 5, 2026 in beta), this is a meaningful upgrade. If you are evaluating coding agents and parallel execution is part of your decision criteria, the Agent Dashboard is the most developed TUI for multi-session work in any terminal coding agent right now. Here is exactly what it does and when to use it. How to Open It Two ways in. From your shell: grok dashboard Or from inside any Grok Build session: /dashboard The keyboard shortcut Ctrl+ also opens the dashboard from any active session. Closing the dashboard does not close your sessions — they keep running. When you reopen it, every session is still there in whatever state it was in when you left. That last point matters. The dashboard is a view, not a session manager. Sessions have independent lifetimes. You can close the dashboard, switch to a different terminal, do other work, and come back to a batch of completed or paused sessions waiting for your attention. Session States and the Sorting Logic Every session in the dashboard shows one of three states: working , awaiting input , or idle . The dashboard sorts them automatically, with sessions waiting for your input at the top. Working sessions come next. Idle sessions sit at the bottom. The practical result: open the dashboard and the first thing you see is your blocker queue. Sessions that need you are at the top. Everything else is running or done. You do not have to mentally track what state each terminal is in — the sort does that for you. Selecting any row shows the session's latest output inline, without opening the full conversation
Activists raised a 40-foot-tall inflatable Elon Musk in Manhattan to draw attention to the risk he allegedly poses to investors.
I’ve spent a lot of time lately thinking about why some LLM agents feel "intelligent" while others just feel like chatbots with a slightly better prompt. It almost always comes down to how the system handles memory. When we treat the context window as the only place for state, we hit a ceiling very quickly. To build an actual agent, we have to move away from "one big prompt" and toward a layered memory architecture. Agentic Memory can be categorized in 4 layers by their function: Working Memory: The current context window. It's our RAM—fast, essential, but wiped clean after every session. Semantic Memory: The Vector DB or knowledge base. This is where the "world rules" and global conventions live. It’s the reference manual the agent checks to stay aligned. Procedural Memory: The "how-to" layer. Instead of stuffing every tool description into the prompt, the agent maintains a lean index of skills and pulls in the full implementation only when a specific task triggers it. This keeps the context window clean. Episodic Memory: This is the hardest part. It's the ability to distill a past interaction into a reusable insight. The real engineering challenge here isn't storage—it's the "forgetting" logic. Deciding what is noise and what is a core pattern is where most frameworks still struggle. Depending on the use case, the architecture changes: Reflex Agents: Just Working Memory. Support Agents: Working + Procedural. Coding Agents: The full stack. The gap between a demo and a production-ready agent is usually the distance between simple RAG and a functioning episodic memory. The ability to compress experience into a usable state is still a significant hurdle. Which of these layers are you currently implementing, and how are you handling the "forgetting" logic in your episodic memory?