AI 资讯

High-quality video generation and conversational editing Discussion | Link

Telling an LLM that 2 + 2 = 5 is enough to make it follow forbidden instructions.

As high memory and storage prices have driven up the cost of everything from consoles to computers, finding a competent laptop for under $1,000 has become a challenge. Thankfully, the Acer Swift Go 16 AI is on sale for $899.99 at Best Buy, a steep discount from its usual list price of $1,549.99. The well-equipped […]

AI CAD inside Onshape and Fusion Discussion | Link

Google's NotebookLM is adding a new way to catch up on your notes: TikTok-style AI videos. The new feature is rolling out to Google AI Ultra and Pro subscribers, allowing NotebookLM to generate 60-second vertical AI clips based on the sources you upload to the app. The example shared by Google details Australia's unsuccessful war […]

Google is updating its image generator to make it faster and cheaper, making it a more useful tool for creators looking to make AI content.

A conference sold out three separate ticket tiers before the doors even opened. Not "almost sold out." Sold out — Leadership track, gone. Workshops, gone. Late bird tickets, gone. The organizers stopped counting around 6,000 attendees and said they'd officially call it once they crossed 7,000. That's the AI Engineer World's Fair in 2026, and if you've spent any time building with LLMs over the last three years, you already know the name even if you've never been able to get a ticket. I want to walk you through what's actually happening on the ground this week at Moscone West in San Francisco — not the marketing copy, but the track list, the speaker lineup, and the quiet signals buried in the schedule that tell you where AI engineering is actually heading next. Table of Contents What is AI Engineer World's Fair? Why It Matters What Makes It Different Key Technologies AI Agents LLM Engineering MCP RAG Fine-tuning AI Infrastructure Workshops Networking Startups Enterprise AI Major Takeaways Future of AI Engineering Final Thoughts What is AI Engineer World's Fair? AI Engineer World's Fair is the flagship conference run by AI Engineer, the company behind a whole circuit of events — the AI Engineer Summit, Code Summit, and standalone editions in London, New York, Paris, Miami, Singapore, Shanghai, and Melbourne. The World's Fair is the biggest of them all: a four-day event with 29 tracks, 300 speakers, 100 expo partners, and more than 6,000 AI engineers, founders, and VPs of AI in attendance. The 2026 edition runs from Monday June 29 through Thursday July 2, with a Sunday evening orientation night tacked on for first-timers. It's held at Moscone West, 747 Howard Street, in San Francisco. This is the fourth year the event has anchored in San Francisco, and the organizers have leaned into that — discounted hotel blocks at the Marriott Marquis, Parc 55, and InterContinental, all walking distance from the venue. The person behind all of it is Shawn "swyx" Wang. He's the cofou

Security Team: “I have a major Grype...with what I Syfted out of your provided image." Developer: “Well your Grype is slowing me down...let’s tone it down a notch.” While deploying bookstack into my local environment, this issue surfaced. It is true for many organizations today deploying images and packages in their environment. How can this noise fatigue in the software supply chain be remedied? Add a .gype.yaml file to the root directory of your project. This will allow grype to ignore certain CVE's that do not execute or pose a threat in your environment. The yaml config can be as simple as below: Linux Environment # grype.yaml ignore : - vulnerability : CVE-2026-32631 reason : " Platform-specific false positive. Git for Windows only; not applicable to this Linux-based image." - vulnerability : CVE-2016-2781 reason : " Chroot escape via ioctl. Containers rely on namespaces/cgroups, not chroot, so this path isn't exploitable here." OR # grype.yaml ignore : - vulnerability : CVE-2026-32631 - vulnerability : CVE-2016-2781 This will help developers and security engineers get along better. 😃 Grype config reference: https://oss.anchore.com/docs/reference/grype/configuration/

Key Takeaways Oracle Backend for Microservices and AI 2.1.0 is a platform modernization release. It updates several shared backend concerns at once, including external access, observability, configuration, messaging, database deployment choices, workflow, samples, enterprise installation planning, and upgrades. Gateway API and Envoy Gateway are now the default external access direction. NGINX Ingress Controller is deprecated, disabled by default, and still available only when explicitly enabled. The release gives platform teams clearer building blocks. OpenTelemetry Operator, Java auto-instrumentation, Spring Config Server, Kafka through Strimzi-managed resources, and clearer database deployment choices supported by Oracle AI Database Operator for Kubernetes make important platform choices easier to see and discuss. Enterprise adoption still needs architecture review. Before adopting or upgrading, teams should review private registry needs, air-gapped installation requirements, multi-tenant installation goals, workflow implications, database deployment choices, and upgrade readiness. OBaaS 2.1.0 is a platform modernization release Oracle Backend for Microservices and AI , or OBaaS , is a backend-as-a-service style platform for teams building microservices and AI-enabled applications with Oracle AI Database as a core data foundation. It brings common backend platform concerns together: service access, telemetry, configuration, messaging, workflow, and database connectivity. That matters because most teams do not want every application squad to rebuild those pieces on its own. They want a platform shape that gives developers useful defaults while still giving architects, DBAs, security teams, and operators the control points they need. This article focuses on the Oracle Backend for Microservices and AI 2.1.0 update. The best way to read OBaaS 2.1.0 is not as a single-feature release. It is a platform modernization release. The update moves the default external access

After several weeks of optimization and community feedback, AnimaStage Lite v1.2.3 is now available. The biggest milestone of this release is that AnimaStage Lite is now available on Google Play, alongside the browser version. 📱 Google Play https://play.google.com/store/apps/details?id=com.webmmd.suite 🌐 Browser https://animastage-lite.app What's new in v1.2.3 📱 Google Play Release AnimaStage Lite is now officially available on Android through Google Play, making it easier to access the editor without manually installing APKs. ⚡ Multi-model performance improvements Working with multiple characters is now much smoother. Improvements include: Performance governor now reacts to the number of visible models. Background characters use a lighter rendering path. When playback is paused, Bullet Physics is simulated only for the selected character. Bullet Physics substeps are capped to improve stability and maintain FPS. 🔄 Physics stability A new Global Physics Stability Registry helps keep simulations more reliable across different scenes. Added: Fix Physics — a soft physics reset that restores the simulation without interrupting the animation timeline. This was implemented after feedback from users who experienced unstable physics when working with multiple models. 🛠 Bug fixes Fixed: SITE_URL is not defined in officialProject.ts General stability improvements Various internal cleanups Project goals AnimaStage Lite is an experimental browser-native MikuMikuDance studio built with WebGL and WASM. Current features include: PMX / PMD support VMD animation playback Bullet Physics Timeline editor MP4 export Browser + Android support The long-term goal is to make MMD creation accessible without requiring a desktop installation. Links 🌐 Website https://animastage-lite.app 📱 Google Play https://play.google.com/store/apps/details?id=com.webmmd.suite 💻 GitHub https://github.com/FBNonaMe/animastage-lite Feedback, bug reports, and feature suggestions are always appreciated. Every relea

INTRODUCTION When I started using Power BI, I only thought of visuals like charts and graphs. However, as I progressed, I discovered a great data dashboard is built on great data models. Data Modelling is the process of organizing your data tables and defining how they relate to each other so Power BI can combine them into meaningful reports and dashboards. Good, designed data makes it easier and faster to maintain. Why is data Modelling Important Well-organized data makes it easier to manage data. Reduction of the duplicates. Ensures data consistency. Understanding Relationships Relationships allow the data table to give communication using fields. For example, Customer Table stores all information about a customer. Product Table store product details Sales Table stores all information about the transactions. Power BI connects the information between the customer’s name and Customer Id rather than repeating them it connects the information using joins. Going through relationships I discovered schemes. Scheme is the way tables are organized in databases. There are different types of schemes e.g. Star Schema, snowflake schema and Flat table. Star Schema A star schema is a data model with one central fact table and dimension table surrounding it. Fact table A table that stores events, transactions of what happened. • Total sales • average sales • quantity sold Dimension table A dimension table describes the items in the fact table. The table contains descriptive information. • The customer table describes the customer • How much sales were made The fact table sits in the center, while the dimension tables surround it—forming a star. Dashboard designs A good dashboard has to fit one page. A dashboard should show critical information. Update automatically when data changes. Focus on data understanding and decision making. Conclusion Power BI taught me that a great report are built from a a great dashboard which is achieved by having great models. Structuring a data into

Of all the things involved in turning a woman's life into a 60-second reel, I assumed that the writing would be the easy part. Surely telling a good story in 150 words is exactly what a large language model should be good at; yet it proved surprisingly difficult. Draft after draft suffered from common AI weaknesses: a tendency to use hyperbole and inspirational language, to generalize, follow generic founder arcs ("built in a basement"), and focus on morbid details. (For this effort, I was using Sonnet 4.6, which I found to be better — more grounded, more true to facts, less inventive — than Opus 4.7 at creating longer bios.) Getting to something publishable took a significant amount of work. That said, the human in this story also found writing good short story arcs surprisingly challenging, so the effort spent on getting the system to do it decently was well worth it. Here's some context, then what I did. I've been publishing short biographies of notable women for a while now, on a website called Tycoona . Why notable women? Because in each field there are so many women who contributed so much and are little known. I've never understood why Corita Kent , the pop-artist nun, isn't as famous as Andy Warhol, why Hetty Green , the Gilded Age value investor called both the "Witch of Wall Street" and the "Queen of Wall Street," disappears into history behind Benjamin Graham and his protege Warren Buffett. The problem I faced is that no one was seeing my bios, so I decided to make short videos or reels in hopes of increasing my reach. Creating the technical infrastructure for the reels on top of my existing system was fun and relatively straightforward. Each reel consists of a series of "beats," and Remotion turns those beats into a vertical reel, complete with on-screen text and royalty-free images & attributions pulled from Wikimedia, Flickr, or Library of Congress. For content, the beat generator relies on the knowledge base of validated facts that my system creates f

Originally published on PrepStack . Everyone's first RAG pipeline is the same four boxes: documents, chunk, vector DB, LLM. It demos in an afternoon and then quietly betrays you in production — stale answers, no relationships, no governance, and a model guessing from fragments. The fix is not a bigger vector index. It is to stop storing documents and start storing knowledge . That is Open Knowledge Format (OKF). To be clear up front, because the title is deliberately provocative: OKF does not kill embeddings. Vectors still do the recall. What OKF kills is blind chunking — slicing opaque documents into context-free fragments and hoping cosine similarity reassembles meaning. On Mattrx , a multi-tenant marketing-analytics SaaS (.NET 9 + Azure SQL + a Python FastAPI AI service), replacing blind chunking with OKF + a Context Engine took the assistant's hallucination rate from 18% to 3% and stale-answer rate from 11% to 1.5% . TL;DR Dimension Documents → chunk → vector DB (before) OKF + Context Engine (after) Unit of knowledge Opaque chunk of text Typed, governed knowledge unit Structure None — chunks are islands Metadata + relationships + schemas Freshness Snapshot, rots silently valid_until + live API refs Rules Buried in prose, ignorable First-class data the engine enforces Retrieval Top-k cosine Hybrid + vector + graph Multi-hop questions Unanswerable Answered via relationships Results after the rebuild: Knowledge base restructured into ~11,000 OKF units (Markdown + metadata + relationships + APIs + schemas + business rules). Hallucination 18% -> 3% ; faithfulness 0.96 ; answer-relevance 0.91 . Context tokens/call 14k -> 3.5k — structure lets the engine attach the right thing, not everything. Outdated-answer rate 11% -> 1.5% ( valid_until + metadata freshness). Multi-hop questions unanswerable -> answered via graph retrieval. Deprecated-plan recommendations recurring -> 0 (business rules enforced as data). The one mental shift: a chunk is a fragment of text with no id

They may not look as good, but Nano Banana 2 Lite images only take a few seconds to create.

A customer texted me a screenshot last month. It was my own landing page, open on their Pixel. The headline — "Financial infrastructure to grow your revenue" — was clipped at "...grow your reven". The signup button below it was gray-on-slightly-lighter-gray, basically unreadable. And the hero image? A broken-image icon. Here's the part that stung: every check I had was green. Lighthouse: 98. My Playwright tests: passing. CI: all checkmarks. I had shipped that page an hour earlier feeling good about it. None of my tooling caught any of it. I want to walk through why , because I think a lot of us have this blind spot, and then I'll tell you what I did about it. CI tests the DOM. It does not test what a human sees. This is the core issue. My tests asserted things like "the signup button exists" and "the form has an email input." All true. The button was in the DOM . It just rendered unreadable on a 412px-wide screen with the system in light mode. Lighthouse runs one viewport (usually a throttled Moto G4 emulation) and scores performance/SEO/a11y heuristically . It does not look at your page across the actual range of devices your visitors use and say "this headline is physically clipped on a Pixel 8." And my "responsive testing"? I was dragging the Chrome devtools responsive bar to two breakpoints — 375 and 1440 — eyeballing it, and moving on. That's not testing. That's hoping. The three bugs that slipped through Let me get specific, because the category of each bug is instructive. 1. The clipped headline — a measurable, deterministic bug .hero-title { white-space : nowrap ; /* the culprit */ width : 100% ; overflow : hidden ; } On desktop, the headline fit. On a narrow viewport, white-space: nowrap refused to wrap, overflow: hidden clipped the overflow, and the last word vanished. The brutal thing: this is trivially detectable in code . The element's scrollWidth was greater than its clientWidth . That's a one-line check: const clipped = el . scrollWidth > el . clientW

Most teams still treat manual test cases as rows in a SaaS database. That worked when cases were written slowly, reviewed rarely, and automation lived in a separate silo. It works less well now. AI can draft cases from screenshots and user stories in minutes. Automation lives next to application code. QA and dev share the same PRs. Auditors ask where test data lives and who changed what. In that world, test cases are data — and the format you choose matters as much as the tool UI. The durable direction is tests as code : plain YAML files in version control, with a thin local layer for humans to browse, run, and review. Not because databases are evil, but because git + YAML matches how we already work with code, AI, and compliance. 1. AI is good at YAML — and YAML keeps your data yours LLMs are unusually good at structured text: YAML front matter plus a Markdown body is a sweet spot. Give the model a schema ( title , tags , priority , steps, expected result) and a screenshot or user story, and you get a draft case in one pass. That matters for more than speed: Boundary cases — ask the model what you might have missed; it can reason about the scenario, not just paraphrase the story. Consistency — the same format every time makes batch generation and review predictable. The deeper point is data ownership . Cases in a vendor DB are convenient until they are not: export limits, API friction, another system to secure, another place sensitive scenarios live. Local YAML in your repo is trivial for AI to read (including Cursor, Copilot, or whatever you use next), diff, and update — without shipping your test catalog to a third party. For many teams, that is a real security and efficiency win — not ideology. 2. Manual YAML beside automation makes coverage measurable When manual cases and automated tests sit in the same repository, a few things become boring in a good way: Tag a case automated: true and point params at a Playwright or Selenium path — one file, one id. Automati

Just hit this today and I'm furious. I installed the Cursor iOS app to see what it had. I've been on `Privacy Mode (Legacy)` for a long time, which is the "Do not store my code" setting. A year or so ago they marked this as "Legacy" and hid it under a "Extra options" menu. They added a new Privacy Mode which is significantly more wishy-washy about what it might store - it includes a clause of "Code may be stored for Background Agents or Other Features", so I've never touched it or wanted to enab

AI that plans, acts, and gets work done Discussion | Link