标签：#ki

Aggressive training techniques sharpens threat of bad behavior by leading models.

"I don't think you get a model this strong and this quickly on the heels of Fable doing strictly distillation," one expert told TechCrunch.

Here are the best delivery services and meal kits in 2026, including Martha Stewart’s meal service, a GLP-1–supportive plan, and a budget-friendly option.

The risks are real. But banning children from the internet could create new problems without solving the ones that really matter.

Ethereal Bytecode for the Network: Unlocking XDP's Magic! Hey there, fellow tech enthusiasts! Ever felt like the traditional networking stack in your Linux kernel was a bit… sluggish? Like it was taking the scenic route when you needed it to be a supersonic jet? Well, let me introduce you to a superhero that swoops in and turbocharges your network packet processing: eBPF, specifically in the context of XDP (eXpress Data Path). Forget the days of wrestling with complex kernel modules or praying for better hardware offload. eBPF and XDP offer a revolutionary, in-kernel, safe, and incredibly efficient way to program packet processing at the very edge of your network interface. Think of it as giving your network card a tiny, super-smart brain, capable of making lightning-fast decisions before the packet even bothers the main kernel stack. Pretty cool, right? So, buckle up as we dive deep into the wonderful world of XDP and eBPF, demystifying its power and showing you why it's becoming the darling of modern networking. 1. The "What's the Big Deal?" Section: Introduction to XDP & eBPF Imagine a bustling highway (your network). Traditional networking is like having every car stop at a toll booth, get inspected, and then directed by a central traffic controller. This works, but it can get congested. XDP, on the other hand, is like having intelligent on-ramps where some cars can be instantly identified, rerouted, or even rejected before they even hit the main highway. eBPF (extended Berkeley Packet Filter) is the technology that makes this possible. It's a powerful, sandboxed virtual machine that runs within the Linux kernel. Unlike traditional kernel modules, which can potentially crash your entire system if written incorrectly, eBPF programs are rigorously verified by the kernel for safety and correctness before they are allowed to execute. This means you get the power of kernel-level access without the existential dread of a kernel panic. XDP (eXpress Data Path) leverages

TL;DR: nb2lite-skill-kiro wraps Google's gemini-3.1-flash-lite-image model (NB2Lite) in a tiny FastMCP server and packages it as a Kiro skill. You type "generate an image of a cyberpunk kitchen" into Kiro, and it just... does it. Then you say "add a neon RAMEN sign" and it edits the same image without re-prompting the whole scene. Oh, and the cover image of this article? Generated by the thing the article is about — dogfooding all the way down. More on that at the end. Background: why another image tool? Most image-generation workflows are stateless . You send a prompt, you get pixels back, and the model immediately forgets everything. Want to tweak the result? You re-describe the entire scene and pray the character, lighting, and composition survive the round trip. (Narrator: they don't.) Google's NB2Lite — the friendly nickname for gemini-3.1-flash-lite-image — takes a different approach. It's a high-efficiency image model with sub-2-second generations, solid text rendering in 25+ languages, and — the headline feature — support for the stateful Interactions API , which lets you iterate on an image across multiple turns while the model keeps the visual context server-side. This repo glues that capability into Kiro , so your coding agent can generate and iteratively refine images as a natural part of a session. It ships as two things in one repo: A Model Context Protocol (MCP) server ( nb2lite-agent , a single-file FastMCP app in server.py ) exposing exactly four tools. A Kiro skill ( nb2lite-image ) that teaches Kiro when and how to use those tools well. The Interactions API: images with a memory The Interactions API is Gemini's stateful endpoint. The core loop looks like this: You call client.interactions.create(...) with a prompt and store=True . The response includes an interaction_id — a handle to the turn's visual context, persisted on Google's servers. On the next call, you pass previous_interaction_id , and the model edits the existing canvas — preserving ch

Treasury Secretary Scott Bessent warned the U.S. government could sanction Chinese AI companies after White House officials accused Moonshot of distilling Anthropic's Fable model to develop Kimi K3.

What We Learned Building a Location-Aware Contact Management App Most contact apps are built like digital phonebooks. They store a name, phone number, email, maybe a company name, and then leave the user to remember everything else. That works when someone has 50 people saved. It starts breaking when someone has hundreds or thousands of professional connections from events, client meetings, referrals, business cards, conferences, online communities, and local networking groups. The hard part is not storing people. The hard part is helping users find the right person at the right time. While building a location-aware contact management app, we learned that contact data becomes far more useful when it is connected to context: where someone is, how the user met them, what they discussed, what industry they belong to, and why the relationship matters. Here are some product, UX, and privacy lessons we learned along the way. 1. A contact list is not the same as a usable network A normal contact list answers one basic question: “Do I have this person’s number?” But professionals usually need better questions answered: Who do I know in this city? Who did I meet at that event? Which industry contacts are nearby? Who should I follow up with before visiting this area? Who was that consultant I met last month? Which contacts are important but easy to forget? This is where the product problem becomes interesting. A user may technically have the contact, but still fail to use the relationship because the contact is buried inside a long list. So the first learning was simple: Saving contact details is not enough. The app needs to help users retrieve useful relationships when the context matters. That changed how we thought about the product. We were not just designing a place to store people. We were designing a system to make saved professional relationships easier to act on. 2. Location context changes the experience Most contact managers are list-first. You search by name, comp

Meituan's LongCat team shipped a quiet but meaningful update to its open-source talking-avatar stack: version 1.5 swaps the audio encoder, distills sampling down to 8 steps, and adds an INT8 path to fit the model on tighter GPUs. Here's what actually changed under the hood, and which flags you now have to pass. LongCat-Video-Avatar 1.5: DMD2 distillation, Wav2Vec2 replacement, and INT8 offloading LongCat-Video-Avatar 1.5 is an audio-driven talking-avatar generator that turns one portrait plus an audio clip into a lip-synced video with head motion, expression, and body dynamics. Released May 21, 2026, it is an avatar head built on the 13.6-billion-parameter dense LongCat-Video diffusion transformer [base model, Oct 2025]. The headline change: v1.5 replaces the Wav2Vec2 audio encoder used in v1.0 (Dec 16, 2025) with Whisper-Large-v3, which the team attributes to smoother, more natural lip dynamics. Three new flags define the v1.5 workflow, none of which exist in v1.0: Flag What it does Notes --use_distill Enables DMD2-based step distillation, collapsing generation to 8 NFE Mandatory for v1.5 — omitting it falls back to the full-chain v1.0 sampling schedule, not an 8-step path --use_int8 Loads the 13.6B dense DiT in INT8 to cut VRAM pressure Main lever for consumer GPUs --resolution Selects 480P or 720P output New in 1.5 Under the hood, the technique report describes Cross-Chunk Latent Stitching, which removes redundant VAE decode/encode cycles between autoregressive chunks, enabling seamless minutes-long generation without re-encoding overhead [arXiv:2605.26486]. That matters for long-form output where earlier tools drift or stutter at chunk boundaries. One caveat worth flagging before you invest a GPU-hour: Meituan claims parity-or-better results versus HeyGen, Kling Avatar 2.0, and OmniHuman-1.5 across 508 image-audio pairs, 770 crowdsourced evaluators, and 13,240 judgments [human-eval benchmark]. That evaluation is entirely author-controlled and reported as win-rat

Nuxt vs SvelteKit. Which one is better? That is is what I've been testing out this week. I built the...

A new type of malware can worm deep into AI coding systems to steal data and logins—and can flip a “death switch” to destroy files and keep out real users.

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

It starts at just under $25,000, but the hybrid won't arrive until next year.

Talk of banning Chinese-made open-weight LLMs reveals the challenge of turning AI into a business.

Two critical security flaws in WordPress’ software have given hackers the chance to remotely take over tens of millions of websites, according to an estimate by a cybersecurity researcher.

Here's a problem every agent builder eventually runs into: your assistant needs to be good at a lot of things. Writing SQL. Composing emails. Debugging code. Maybe more later. So where do all those instructions go? The obvious answer is: cram them all into the system prompt. But that "obvious" answer causes real problems as your agent grows. In this post, I'll walk through those problems first, then show how the skills pattern in LangChain fixes them, using a small working example. The problem: one giant prompt Let's say you want a single assistant that can write SQL, draft emails, and help debug code. The naive approach is one big system prompt: You are a helpful assistant. When writing SQL: - Write queries using only SELECT, INSERT, UPDATE, DELETE - Always use parameterized queries to prevent SQL injection - Format SQL keywords in UPPERCASE - Include brief comments for complex queries When writing emails: - Keep emails concise and professional - Use clear subject lines - Structure: greeting -> purpose -> details -> call to action -> sign-off - Adjust tone based on context When debugging: - First reproduce the error - Check logs and error messages - Isolate the root cause - Suggest a fix with explanation ... This works fine for three domains. But keep adding more — legal reviewing, data analysis, customer support scripts, code review standards — and you run into a few concrete issues: 1. Prompt bloat. Every single request pays the token cost of every domain's instructions, even if the user only asked about SQL. That's slower and more expensive for no benefit. 2. Instructions start to blur together. When the SQL rules, the email rules, and the debugging rules all sit in the same block of text, the model has to sift through everything at once. It's easy for instructions from one domain to bleed into another, or for the model to lose track of which rule applies where. 3. It doesn't scale. Every time you want to add a new specialty, you're editing one long, increasingl

local + echo = locho Sometimes you don't need access to a machine. You don't need a shell. You...

Introduction Linux is the backbone of modern infrastructure. From cloud servers and firewalls to SIEM platforms and security tools, Linux runs silently behind most enterprise environments. For a Security Operations Center (SOC) analyst, understanding Linux is not optional — it is a core skill. One of the most critical security mechanisms in Linux is its file permission and ownership model. Attackers abuse permissions to execute malware, hide persistence, escalate privileges, and erase evidence. SOC analysts rely on permission analysis to detect anomalies, investigate incidents, and build accurate timelines. Become a Medium member This article covers Linux File Permissions and Ownership in deep detail from a SOC analyst’s perspective. It is designed to take you from absolute beginner to security-aware professional, with real-world examples, attack scenarios, and investigation insights. Why Linux File Permissions Matter in SOC In SOC operations, analysts constantly deal with: Authentication logs System logs Application logs Scripts and binaries Configuration files Evidence files during incident response Every one of these objects is protected by Linux permissions. From a SOC perspective: Incorrect permissions = security risk Permission changes = potential indicator of compromise Executable permissions = possible malware Ownership changes = possible log tampering Understanding permissions allows SOC analysts to: Detect unauthorized access Identify privilege escalation Spot malware execution Preserve forensic evidence Reconstruct attacker activity Understanding Linux File Permission Basics Linux follows a Discretionary Access Control (DAC) model. This means: The owner of a file controls who can access it Permissions define what actions are allowed Every file and directory in Linux has: A type Permissions An owner (user) A group These attributes decide: Who can read the file Who can modify it Who can execute it Viewing Permissions Using ls -l The most common command to i

Say "fable-mode" (or "operate carefully," or "high-judgment mode" or "think like fable") in a Claude Code or Codex session, and one line buried in the skill file does most of the work: "Never promote 'plausible' to 'confirmed' in your summary." That single rule is the whole philosophy in miniature — don't let something that merely looks right pass as something that was checked. Fable-mode is not a tool, a model swap, or a set of new commands. It's a behavioral overlay — a skill file at ~/.claude/skills/fable-mode/SKILL.md or ~/.codex/skills/fable-mode/SKILL.md or any other agent you use, that gets loaded into the turn and changes how the agent scopes work, verifies its own claims, and reports results. Nothing about what Agents can do changes. What changes is the discipline around using it. What actually changes The skill is organized into seven blocks, and each one targets a specific failure mode that shows up in normal agent use: Judgment before action. The first move is classification: is this a question, a problem description, or a change request? For the first two, the deliverable is an assessment — investigate and stop, don't start editing files nobody asked you to edit. Irreversible actions (deletes, pushes, overwrites) require a stop-and-confirm, and specifically: "before deleting or overwriting anything, actually look at the target." Verification as the non-negotiable core. This is the section that does the heavy lifting. Every "done" claim needs evidence produced after the last edit — a test run before your final change proves nothing about your final change. Claims get graded on a three-tier scale: Confirmed (you ran it and saw the result), Plausible (the code reads right but you haven't executed it), Assumed (inherited from the user's description). The rule is that you report the grade you actually earned, not the one that sounds better. Reasoning habits. Hold two hypotheses before committing to a diagnosis. Treat your memory of a library's API as a prior

By the end of this article, you'll know: what Kimi K3 actually is, the architecture, the scale, and what changed from the K2 family how to run it today, free in the browser, through the API, or wired into Claude Code, Cursor, Cline, and RooCode which exact model ID and settings unlock the full 1 million token context how K3 stacks up on price and benchmarks against DeepSeek V4, Qwen3.7 Max, GLM-5.2, and its own sibling K2.7 Code whether switching today makes sense, or whether you should wait Kimi K3 just dropped, and Moonshot means business Moonshot AI released Kimi K3 on July 16, 2026, timed just ahead of the World Artificial Intelligence Conference in Shanghai. The Beijing lab, backed by Alibaba, has spent the past 18 months watching DeepSeek erode its market position. K3 is the comeback attempt, and the early numbers back it up. The headline result: K3 debuted at number one on Arena.ai's Frontend Code Arena with a score of 1,679, ahead of Claude Fable 5 at 1,631 and GPT-5.6 Sol at 1,618. Its predecessor, K2.6, sat 18th on that same board. That's a 17 spot jump in one release, and it's independently measured, not a number Moonshot invented itself. This isn't Moonshot's first time in Western production stacks either. Cursor built its Composer 2 model starting from a Kimi K2.5 base. DoorDash's CTO has said the company routes lower level work to Kimi K2.6. Thinking Machines used K2.5 to help generate early post-training data for Inkling, its own model released just a day before K3. So when a new Kimi flagship lands, it lands somewhere developers already have skin in the game. For developers, the practical story matters more than the leaderboard. K3 is open weight, speaks the OpenAI SDK, and drops into tools you already use. It's also, for the first time in Kimi's history, priced like a frontier model instead of a budget one. That changes the calculus on when it's actually worth reaching for. What Kimi K3 actually is K3 is a sparse Mixture-of-Experts model with 2.8 tr