Articles & Guides

The first three operational FireSat satellites have reached orbit, bringing a purpose-built wildfire detection constellation closer to service. Backed by Google and other funders, the system combines multispectral imaging with AI analysis to detect small fires earlier.

TikTok is testing an opt-in tool that scans for AI-generated content potentially using a creator’s likeness without permission. The pilot is currently available to some creators in the US and requires identity verification before use.

Apple’s trade secrets lawsuit against OpenAI could complicate the company’s hardware push and its reported IPO ambitions. The case also raises a broader question: how much trust should companies and users place in AI firms handling sensitive knowledge and data?

The Vergecast examines Apple’s lawsuit against OpenAI as more than a courtroom dispute. The episode frames it as a signal of how AI, devices, and platform power are beginning to collide.

Amazon Web Services has released Claude App Gateway for AWS, a self-hosted control plane for Claude Code and Claude Desktop. The gateway centralizes access control, policy enforcement, routing, telemetry, and spending limits for enterprise deployments.

San Francisco’s city attorney has demanded that Apple and Google remove 13 AI “nudification” apps from their app stores, arguing that the platforms may be supporting services that create illegal nonconsensual intimate imagery.

Patreon is strengthening protections for creator content by working with Cloudflare to block AI training crawlers that attempt to scrape material without permission.

Stripe has released an open benchmark for testing whether AI agents can build complete Stripe integrations in realistic environments. The results suggest that agents can generate and modify code, but still struggle with validation, browser state, and recovery from ambiguous failures.

General Compute has secured a $400 million chip-backed loan from Upper90, using inference-focused silicon as collateral. The deal suggests AI infrastructure financing is beginning to look beyond GPU-heavy training toward cheaper model-serving capacity.

Moonshot AI has introduced Kimi K3 with 2.8 trillion parameters, a MoE architecture, a 1-million-token context window, and native multimodal capabilities. If its full weights are released as planned, it could become the first open-source model in the 3-trillion-class range.

OpenAI CFO Sarah Friar has outlined a practical scorecard for evaluating AI return on investment. The focus is not on flashy demos, but on useful work, cost per successful task, dependability, and return on compute.

OpenAI’s first branded hardware product is not a phone or an AI companion, but a palm-sized programmable keyboard for Codex users. Built with Work Louder and priced at $230, Codex Micro is designed to control AI coding agents.

A related investment progress announcement from Korrun unexpectedly brought DeepSeek’s latest valuation into public view. Based on the disclosed investment ratio, the company’s post-financing valuation is estimated at about RMB 350.877 billion.

According to OSChina’s summary, generative AI music platform Suno suffered a leak involving internal source code and data collection materials, allegedly exposing large-scale scraping of music, lyrics, and audio data for model training.

A new study finds that reinforcement learning with length penalties can compress chain-of-thought reasoning while making it harder to see which influences shaped the model’s answer.

OvisOCR2 converts document page images directly into Markdown in natural reading order, covering text, formulas, tables, and visual regions. Its reported results suggest that compact end-to-end parsers are becoming serious competitors to traditional pipeline-based OCR systems.

A new survey argues that discrete diffusion should be understood through the way its state space is built. Tokenization, vocabulary topology, and domain alphabets shape everything from corruption to sampling.

Ring-Zero studies zero reinforcement learning at the 1T-parameter scale, using verifiable rewards rather than human-annotated reasoning traces. The paper argues that scaling improves sample efficiency and performance ceilings while revealing new reasoning behaviors.

The paper argues that current AI pentesting benchmarks are too controlled to predict real-world performance. It proposes an evaluation protocol centered on validated vulnerability discovery across more complex targets.

The European Commission has finalized binding DMA measures requiring Google to share search data with rivals and give third-party AI assistants deeper access on Android.

xAI has filed its first lawsuit against a Grok user accused of using the chatbot to create child sexual abuse material. The case is also an attempt to frame Grok as a neutral tool and shift legal responsibility to users who violate its terms.