AI 资讯

With the new tools, parents and guardians will be able to view their teen's time spent on Threads, set daily time limits, adjust sleep mode, and manage their privacy settings.

Canvases turn AI into interactive workspaces where you can visualize information, explore workflows, and take action across complex tasks. The post How to build interactive experiences with canvases appeared first on The GitHub Blog .

When a gbase database cluster experiences an unclean shutdown — a sudden power loss or kernel panic — some metadata that was still in memory may never make it to disk. This can leave the critical gbase.table_distribution table with missing rows, causing queries against certain tables to fail with the error: ERROR 1149 (42000): (GBA-02SC-1001) Can't get distribution attribute of table `testdb`.`t2_test`, please check your gbase.table_distribution. The Symptom The affected table enters a contradictory state: Dropping it returns Unknown table . Re‑creating it returns Table already exists . The data files exist on disk, but the metadata record that describes how the table is distributed is gone. Root Cause GBase 8a stores critical table metadata — distribution type (hash or random), replication status, hash column — in the system table gbase.table_distribution . After an abrupt shutdown, this table may have missing entries, causing the cluster to lose track of the table's distribution properties. Recovery Options Option 1: Re‑insert the Metadata Row (Keeps Data Intact) This is the recommended approach when the data must be preserved. Insert the missing row directly into gbase.table_distribution . -- Insert the lost metadata record INSERT INTO gbase . table_distribution VALUES ( 'testdb.t2_test' , 'testdb' , 't2_test' , 'NO' , NULL , NULL , NULL , 'NO' , 2 ); -- Verify the row is now present SELECT * FROM gbase . table_distribution WHERE index_name LIKE '%t2_test%' ; Key fields: isReplicate : YES if the table is replicated, otherwise NO . hash_column : The distribution key column name (if hash‑distributed); NULL for random distribution. data_distribution_id : A numeric ID. Copy the value from another healthy table in the same database to keep it consistent. After inserting, restart the gcluster service so the metadata takes effect (the table_distribution table is managed by gcluster, not gnodes): gcluster_services gcluster restart The table should now be queryable again.

Open-source LLMs stopped being the budget option in 2026. Kimi K3 sits level with Claude Opus 4.8 on the Artificial Analysis Intelligence Index (its hosted API is live; the weights themselves are expected by July 27), GLM-5.2 held the top open-model spot before it, and the field behind them is deep enough that the hard part is choosing. This ranking covers the nine best open-weight models right now — on license, context window, hardware reality, and the per-token price you actually pay. Every one of them is available through LLM Gateway with one key, at each provider's published rate, so you can A/B any two of them by changing one word in a request. 1. Kimi K3 — the open frontier Moonshot AI · 2.8T params · 1M context · $3.00 / $15.00 per M The largest open-weight model ever announced — with one caveat: the weights are not downloadable yet. Moonshot expects to release them by July 27, 2026, and the license is still unannounced; the hosted API has been live since July 16. Ranks 4th of 189 models on the Artificial Analysis Intelligence Index — tied with Claude Opus 4.8 and GPT-5.5 — and took first place in Arena's blind Frontend Code testing. Always-on reasoning, vision, tools, and output configurable up to 1M tokens. The open model to beat, priced accordingly. Full breakdown here . Best for: teams that want closed-frontier quality with open-weight freedom. 2. GLM-5.2 — the value flagship Z.ai · 744B params · 1M context · $1.40 / $4.40 per M MIT-licensed, weights on Hugging Face, and the top-ranked open model until K3 arrived. A real 1M-token context, strong agentic-coding results, and built-in web search support — with output at under a third of K3's rate and input at about half. Also the largest model on this list that fits a single 8-GPU node (or one 512 GB Mac Studio) at INT4. Best for: the best capability-per-dollar in the open field. 3. DeepSeek V4 Pro — frontier scale at commodity prices DeepSeek · 1.6T params (49B active) · 1M context · $0.435 / $0.87 per M MI

Kimi K3 took first place in Arena's Frontend Code evaluation the week it launched, and it holds a 1M-token context — but Moonshot doesn't ship a coding agent, and your coding agent doesn't ship Kimi K3. Claude Code is locked to Anthropic's API by default, Cursor to its own backend, Cline to whatever key you hand it. LLM Gateway bridges that gap. It speaks both the Anthropic and OpenAI API formats, so the tools you already use can run Kimi K3 — or any of 200+ models — with a base-URL change. Here is the exact setup for each tool. Kimi K3 in Claude Code Claude Code talks to any endpoint that speaks Anthropic's /v1/messages format, which LLM Gateway does natively. Three environment variables: export ANTHROPIC_BASE_URL = https://api.llmgateway.io export ANTHROPIC_AUTH_TOKEN = $LLM_GATEWAY_API_KEY export ANTHROPIC_MODEL = kimi-k3 claude That's the whole migration. Every request now routes through LLM Gateway to Kimi K3, and every request shows up in your dashboard with its exact cost, token counts, and cache-hit rate. One refinement worth adding: Claude Code uses a second, smaller model for routine background work, and you can point it at something cheap — or free: export ANTHROPIC_SMALL_FAST_MODEL = glm-4.7-flash-free That puts K3 on the hard reasoning and a $0 model on the housekeeping. Kimi K3 in Cursor Cursor routes its chat / plan panel (Cmd/Ctrl + L) through a custom OpenAI-compatible endpoint. Setup: Open Cursor Settings → Models Add your LLM Gateway key under OpenAI API Key Enable Override OpenAI Base URL and set it to https://api.llmgateway.io/v1 Add kimi-k3 as a custom model and select it Be aware of the boundary: Cursor's Composer, inline edit (Cmd/Ctrl + K), and autocomplete are locked to Cursor's own backend and will not route through any external endpoint. Plan and chat with K3's full 1M context in Cursor; if you want K3 driving the actual agent loop, use Claude Code or Cline instead. Kimi K3 in Cline Cline is the straightforward one — it's built to bring y

Kimi K3 is the first open-weight model that makes the Kimi K3 vs Claude Opus 4.8 question worth asking seriously. On the Artificial Analysis Intelligence Index, K3 ranks fourth of 189 models — level with Opus 4.8 and GPT-5.5, behind only Claude Fable 5 and GPT-5.6 Sol. It also costs 40% less per token, and its weights are expected to be released by July 27. The honest answer is not "K3 wins" or "Opus wins" — it depends on what you're optimizing for. Here are the numbers, then the verdict. Benchmarks: Kimi K3 vs Claude Opus 4.8 Benchmark Kimi K3 Claude Opus 4.8 Artificial Analysis Intelligence Index 57 (4th/189) statistical tie GPQA Diamond 93.5% 93.6% Terminal-Bench 2.1 88.3%* 74.6%* SWE-bench Verified not published 88.6% Arena Frontend Code 1st (1,679) ranked below *Reported on different harnesses (Opus 4.8's score uses the Terminus-2 harness), so treat the Terminal-Bench gap as directional, not exact. Three takeaways. On graduate-level reasoning (GPQA Diamond) the models are statistically tied. On agentic terminal work, K3's published number is well ahead, with the harness caveat above. And in Arena's blind Frontend Code testing, developers ranked K3 first outright — ahead of every model, including Anthropic's. Where Opus 4.8 keeps an edge: SWE-bench Verified at 88.6% is a published, battle-tested result K3 has no counterpart for yet, and Anthropic's models remain the default target for agent harnesses — Claude Code, MCP tooling, and most agentic scaffolds are tuned against Claude first. K3 is three days old; its ecosystem is not. Pricing: 40% cheaper across the board Per-token rates through LLM Gateway (each provider's published pricing): Per million tokens Kimi K3 Claude Opus 4.8 Input $3.00 $5.00 Cached input $0.30 $0.50 Output $15.00 $25.00 Both have a 1M-token context window. K3's output limit defaults to 131K tokens but is configurable up to the full 1M in a single response; Opus 4.8 caps output at 128K. Concrete math: a coding-agent workload of 100M input a

Moonshot AI released Kimi K3 on July 16, and the benchmarks put an open-weight model next to the best closed ones for the first time. The catch is access. K3 sits on Moonshot's platform, GLM-5.2 on Z.ai's, DeepSeek V4 Pro on DeepSeek's, MiniMax M3 on MiniMax's — four accounts, four billing relationships, four API dashboards, all before you have written a line of code. LLM Gateway routes every one of them through a single OpenAI-compatible endpoint. One key, one bill, and a switch between Kimi K3 and any of 200+ models is a one-word change to your request. What is Kimi K3? Kimi K3 is Moonshot AI's flagship model for long-horizon coding and agentic work. At 2.8 trillion parameters — a mixture-of-experts design that activates 16 of its 896 experts per token — it is the largest open-weight model announced to date. Moonshot has committed to publishing the full weights by July 27, 2026. The specs that matter in practice: 1M-token context window (1,048,576 tokens), with output configurable up to the same 1M — enough to hold a large repository plus its docs in a single request Always-on reasoning — K3 thinks before every answer; there is no non-thinking mode Vision, tool calls, and JSON output supported out of the box Prompt caching at a 90% discount on repeated input Early results back up the size. K3 ranks fourth of 189 models on the Artificial Analysis Intelligence Index — level with Claude Opus 4.8 and GPT-5.5 — and took first place in Arena's Frontend Code evaluation in blind developer testing. It posted 93.5% on GPQA Diamond and 88.3% on Terminal-Bench 2.1, the strongest open-weight results published on both at release. Kimi K3 pricing Through LLM Gateway you pay Moonshot's published per-token rates: Tokens Price per million Input $3.00 Cached input $0.30 Output $15.00 The cached-input rate is the number to watch. Coding agents re-send the same system prompt, file context, and conversation history on every step, so in a long agent session most of your input tokens are

After five years of shipping features at Tittri, the team gave me a piece of feedback that stung a little: I was good, but I only ever built what I was asked to build. And we delivered, end to end, every week. From dashboards to multi-step workflows to third party integrations, all of it to make dense workflows understandable. Somewhere along the way I'd become all about business critical web apps, where the frontend is not just visual, it's how people execute operations reliably. But it just wasn't enough for me. So in January 2026 I stopped waiting to be asked, and pitched an AI integration into a UK-based fintech client's product, one that handles real business loans. When I finally presented the idea to the team and the client, after enough brainstorming and planning and identifying the best way for the brokers to benefit from it, expectations rose. No prior AI integration experience, no matching tutorials, real users, real data, real money. Then I had to actually build it. What is the client and why AI The client is one of the UK's pre-eminent business finance brokers and comparison services that combines advanced technology with a team of finance experts to help small and medium-sized enterprises (SMEs) and their advisors find, compare, and apply for the most appropriate and affordable funding options from across the entire market. The client's B2B product is a commercial finance brokerage SaaS, where brokers manage deals, calls, emails, documents, lenders, AIPs (Agreement In Principle), credit/KYC, corporate structures, properties...etc. The brokers use the SaaS to run the whole lifecycle of a deal, and before AI every single step of it was manual. A typical deal goes like this: An enquiry comes in by call or email, something like "my client needs £400k to buy out a GP partner". The broker gets on a discovery call that can run 30–90 minutes, writes up the notes afterwards, creates the deal, and then starts gathering everything a lender will want to see. Finan

Originally published at https://eveningdesk.cloud/blog/woocommerce-customer-support-workflow.html . WooCommerce support often starts in a shared mailbox and ends in several tabs. A customer asks where an order is. An agent searches the inbox, opens the store admin, finds the order, checks fulfilment, then returns to write a reply. That sequence is manageable at low volume. It becomes fragile when several people share the work or when the same question arrives all day. The goal is not to add a complicated service desk. It is to make the support workflow reliable: one owner, the right order context, and a reply a human has reviewed. Start With One Support Inbox Use a dedicated address for customer questions, such as support@yourstore.com , rather than mixing them with supplier, marketing, and personal email. Every incoming request should have a clear status: New, when nobody has handled it. Assigned, when one person owns the reply. Waiting, when the customer or carrier needs to respond. Resolved, when no further action is needed. The important part is ownership. If two people read the same message and neither knows who is replying, the customer waits. If both reply, the customer receives conflicting information. Keep Order Context Beside the Conversation Support agents should not guess about an order. A useful workflow links the conversation to the order reference, then checks the information that matters for the question: Order number and purchase date. Payment and fulfilment status. Items, quantities, and shipping method. Tracking or carrier information, when it exists. Previous support messages about the same order. For a connected WooCommerce store, eveningDesk can sync an order record into the support workspace. The agent still reviews the information and decides what to promise. The software provides context. It does not invent delivery dates or approve refunds on its own. Use a Repeatable Reply Process Most store questions fall into a small set of categories: d

Most "contact us" forms on freelancer and agency sites do the same thing. A visitor types a message, hits send, and the message lands somewhere in an inbox. There is no structure to it. You cannot tell what service someone wants, what their budget looks like, or how urgent the project is until you open the email and read it line by line. A quote request system fixes that. Instead of one open text box, you ask the questions that actually help you price and prioritize work: what kind of project this is, what the scope looks like, what budget range they have in mind, and how soon they need it done. Every submission arrives already sorted. In this tutorial, you will build a complete quote request system in React. Not just a form, a full pipeline: a form component that collects structured project details, client-side validation, a submit handler that posts to a backend, an instant email notification, and a lead management view where you can track every request from New to Contacted to Converted. Here is the architecture you are building: Form Component -> Validation -> Submit -> Backend API -> Email Notification -> Lead Management The frontend is plain React. For the backend, email notification, and lead management pieces, you will use Formgrid, an open-source form backend, so you can focus this tutorial on the part that actually needs your attention: building a form that captures the right information and converts. What You Are Building A multi-field quote request form in React with: Full name, email, company, and phone fields A radio group for the type of work being quoted A textarea for project scope Radio groups for budget range and timeline Client-side validation before anything gets submitted A loading state while the request is in flight A success state once the request lands On the backend side, every submission becomes: An instant email notification to your inbox A row in your Formgrid submissions dashboard A tracked lead with a status of New, which you can move

How Normal Software Engineers Actually Use AI in Their Daily Work Let's cut through the hype. You're not building the next AGI. You're a working software engineer with deadlines, legacy code, and a backlog that never shrinks. So how do you actually use AI tools in your day-to-day work? After surveying hundreds of developers and reflecting on real-world usage patterns, here's what normal software engineers are doing with AI—no Silicon Valley theatrics required. The Mundane But Invaluable: Code Completion and Boilerplate The most common use case is the least sexy: letting AI handle repetitive code. GitHub Copilot, Cursor, and similar tools excel at generating boilerplate that you'd otherwise copy-paste from Stack Overflow or previous projects. Real example: Writing CRUD endpoints in Express/TypeScript: typescript // Type this comment and let AI complete: // Create a REST endpoint for user registration with email validation app.post('/api/users/register', async (req: Request, res: Response) => { try { const { email, password, name } = req.body; // Email validation const emailRegex = /^[^\s@]+@[^\s@]+\.[^\s@]+$/; if (!emailRegex.test(email)) { return res.status(400).json({ error: 'Invalid email format' }); } // Check if user exists const existingUser = await User.findOne({ email }); if (existingUser) { return res.status(409).json({ error: 'User already exists' }); } // Hash password and create user const hashedPassword = await bcrypt.hash(password, 10); const user = await User.create({ email, password: hashedPassword, name }); res.status(201).json({ userId: user.id, email: user.email }); } catch (error) { res.status(500).json({ error: 'Internal server error' }); } }); Did AI write perfect code? No. But it gave you scaffolding to refine, saving 10-15 minutes of typing. That's the real win. The Game-Changer: Explaining Legacy Code and Obscure APIs Every developer inherits someone else's mess. AI tools shine when deciphering undocumented code or unfamiliar libraries. Pract

The first Lego X-Files set costs $200 and will be available in August.

I've spent my career helping people build software. This is a series of letters about what happens when the tools for building change faster than the principles behind building. Each one is a reminder that while the technology changes quickly, the questions that matter often stay the same. -- Dear past Jenna, The thing that drew you to tech in the first place, that it's always changing, is the thing that will keep you here. Tools change (sometimes for the better and sometimes not) almost weekly. People who never consider themselves technical, much less a developer, will build apps in an afternoon with this new programming language called English. Products will go from idea to deployed before you finish your first cup of coffee (you have a toddler now, so you rarely get the full cup before it goes cold anyways). "I don't know how to code" or "I'm not technical" is no longer a barrier to building. And that's exciting, given you've focused nearly your entire career helping others build software. But we can't confuse the ability to build with the wisdom to build. One of the most valuable habits you've developed over the last two decades is asking a simple question: "Should we build it?" For most of your career, "Can we build it?" was a hard question. Time, budget, complexity, maybe the tech wasn't there yet. But those constraints were usually temporary. With enough people, time, and money, just about anything is possible. But the real questions were always: Should we build this? Is this the best use of our time? Does this solve a problem our customers actually need solved, or does it create new problems? What are we choosing not to build? Those questions haven't changed, but the environment around them has. Today, almost anyone can build software. Between tools like Lovable, Bolt, Replit, Claude Code, Codex, and whatever's next, the barrier to building software is lower than it's ever been. Now the question "Can we build it?" is too easy to answer. It's almost always ye

You followed an old breeding guide. You put Penking + Bushi into your breeding farm, dropped the cake, waited for the egg... and out hatched Sibelyx , not the Anubis the guide promised. You're not alone. Your guide isn't broken. The recipe changed. When Palworld hit 1.0, the breeding table got quietly rewritten. Almost every pairing that players had memorized from early-access now produces a different Pal. There's no in-game notice, no patch note that lists the hundreds of changed combos — just a lot of confused hatchings. So I dug into the data. Here's what I found, and the small tool I built to make sense of it. What actually changed in 1.0 I compared two snapshots of the game's breeding data — the pre-1.0 set and the current 1.0 release — both sourced from the open-source PalCalc project. The headline number: 97.7% of comparable pre-1.0 parent pairs now produce a different Pal. That's not a typo. If you take the breeding pairs that existed before 1.0 and run them against the current data, nearly all of them hatch something new. A few concrete examples players keep running into: Old recipe (pre-1.0) What it makes now (1.0) Penking + Bushi Anubis → Sibelyx ... (more pairs in the tool) The mismatch matters because most breeding guides and calculators on the internet still show the old results. Players follow them, breed, and get confused. The subtle trap: renumbering vs. real change There's a detail that trips up every breeding tool that tries to track this. When Palworld 1.0 launched, it also renumbered parts of the Paldeck (Pal #139 vs #116, etc.). A naive diff tool would see the number change and wrongly report "the breeding result changed!" — when really only the number changed, not the actual Pal. To avoid that false signal, I match Pals by their internal game name , not their Paldeck number. A renumbering is not mistaken for a changed breeding result. Only genuine recipe changes are counted. The tool: PalShift I wanted a dead-simple way to answer one question:

Treasury Secretary Scott Bessent said the U.S. could sanction Chinese open AI models over alleged IP theft, expanding the Trump administration's campaign to slow China's AI advances.

I'm the developer of DeviceShelf, a local-first network scanner for desktop, mobile and a headless server edition. Until this week the iOS app only existed on TestFlight. Apple has now approved version 1.3.0, so for the first time you can get it straight from the App Store: DeviceShelf on the App Store . What the app does on a phone The iOS app is not a companion viewer. It runs the same scanning engine as the desktop version: it scans the network you're on, identifies devices (vendor, type, OS fingerprint), shows open ports per device, builds a security report, and raises presence alerts when devices appear or drop off. You can export and share results from the phone. The multicast entitlement iOS restricts multicast traffic for ordinary apps, and SSDP/UPnP discovery depends on it. Apple grants the multicast entitlement on request, and DeviceShelf's App Store build has it. In practice, UPnP/SSDP devices show up in scans on the phone the same way they do on desktop. Licensing The download is free and comes with a trial. Full features unlock in one of two ways: activate a DeviceShelf license, which covers desktop, mobile and the server edition with a single purchase, or use the in-app purchase upgrade on iOS. Pricing is on the website if you want the details. Local-first, on mobile too Scans stay on the device. There is no cloud account, and the AI-assisted device identification is bring-your-own-key; no key is bundled or required. The app is still young, and a phone is an unforgiving place for a network scanner. If it mislabels a device on your network or misses one entirely, I'd genuinely like to hear about it. Website: deviceshelf.app

Brain-like knowledge base with AI writing & deep research Discussion | Link

Rspack, developed by ByteDance, has released version 2.0, featuring enhanced performance, reduced dependencies, and a focus on modern ECMAScript modules. Key updates include a pure ESM core, improved static analysis, and support for RSC. Performance benchmarks show big improvements in build times. The project has experienced substantial growth, with npm downloads exceeding 5 million weekly. By Daniel Curtis

The Cirqa Smart Band is Garmin's answer to Whoop and the Fitbit Air.