AI 资讯

“The government believes it has become aware of a method of bypassing, or ‘jailbreaking’ Fable 5,” the company said in a blog post.

On June 10th, the German container ship Posen docked in Los Angeles after a two-week voyage from Shanghai. As Valve watcher Brad Lynch notes, it was almost certainly carrying the first mass production shipments of the Steam Frame, Valve's new gaming headset. Import records show that Valve's distribution partner Ceva offloaded nearly 32 metric tons […]

All tests run on an 8-year-old MacBook Air. All results from shipping 7 Mac apps as a solo developer. No sponsored opinion. After 7 Tauri apps, I type the same commands constantly. Here's the reference I wish existed when I started. Project setup # New project npm create tauri-app@latest # Add to existing project npm install --save-dev @tauri-apps/cli npx tauri init Development # Dev mode (hot reload) npm run tauri dev # Dev with specific log level RUST_LOG = debug npm run tauri dev # Dev with backend logs visible npm run tauri dev 2>&1 | grep -v "^$" Building # Standard build npm run tauri build # Universal binary (Intel + Apple Silicon) npm run tauri build -- --target universal-apple-darwin # Debug build (faster, no optimization) npm run tauri build -- --debug Plugins npm run tauri add global-shortcut npm run tauri add fs npm run tauri add shell npm run tauri add notification This updates both Cargo.toml and the plugin registration. Faster than doing it manually. Permissions (tauri.conf.json) { "app" : { "security" : { "capabilities" : [ { "identifier" : "main-capability" , "description" : "Main window capabilities" , "windows" : [ "main" ], "permissions" : [ "fs:read-all" , "fs:write-all" , "shell:execute" , "global-shortcut:allow-register" ] } ] } } } Tauri v2 requires explicit permission declarations. If a command silently does nothing, check permissions first. Common Rust patterns // Get app data directory let data_dir = app .path () .app_data_dir () .unwrap (); // Emit event to frontend app_handle .emit ( "event-name" , payload ) .ok (); // Get window let window = app .get_webview_window ( "main" ) .unwrap (); // App state app .manage ( MyState :: new ()); let state = app .state :: < MyState > (); Notarization (macOS) # Submit for notarization xcrun notarytool submit app.dmg \ --apple-id YOUR_APPLE_ID \ --team-id YOUR_TEAM_ID \ --password YOUR_APP_PASSWORD \ --wait # Staple after notarization xcrun stapler staple app.dmg Debugging # Check what's in the bundle

I have been frustrated with YouTube for a while. Not the content, but the everything around it. The homepage full of bait, the auto-play into things I didn't ask for, the Shorts that hijack your scroll, the recommendations that somehow know exactly what will keep you there longest. So I built NoSuggest. What it is A YouTube feed reader that shows you only the channels you follow, nothing else. No algorithm, no recommendations, no Shorts, no homepage, no auto-play, no endless side cards of videos. You add a channel, it fetches their latest videos, done. It lives at nosuggest.com and installs as a PWA on any device — iPhone, Android, desktop — straight from the browser. No app store. The interesting technical constraint: one HTML file The entire app is a single index.html. No account setup, no sign-in, no data collection. Everything that needs to persist — your channel list, saved videos, settings — lives in localStorage. No search history. No watch history. No "you might also like." No trending section. No notification badges designed to create anxiety. No dark patterns anywhere. Every time I was tempted to add something convenient, I asked: does this serve the user's intention, or does it serve engagement? If it was the latter, it didn't make the cut. Try it nosuggest.com — Source Available here , free forever. Curious what others think about this as useful. Thank you.

My voice agent took 1.2 seconds. Users hated it. So I made it lie. A while back I shipped a voice agent that took roughly 1,200ms to respond. Not catastrophic on paper. Pretty bad in practice. Users would ask a question, get a beat of silence, and start over. Some thought the mic had cut out. One tester told me, with a straight face, that my agent was "thinking too hard." I tried everything legitimate first. Smaller LLM. Streaming TTS. Region-pinned endpoints. I shaved off about 200ms and felt clever for a week. Then I measured again and realized I was still on the wrong side of every latency threshold that matters. So I gave up on being faster and started working on being a better liar. This is the playbook I wish I had when I started: five perception tricks that reduce felt latency without touching the actual numbers. They're the voice-AI equivalent of a magician's misdirection. Your right hand waves at the audience. Your left hand swaps the card. The cliff you can't engineer your way out of In a previous article I broke down the three latency cliffs for voice AI. The short version: Around 200ms : the brain starts to register the pause as "slow." This is the conversational baseline humans use with each other. Around 500ms : the conversation breaks. The user starts to wonder if they need to repeat themselves. Around 800ms : they've quietly given up. Even if your answer arrives, the trust is gone. If your stack is doing STT plus LLM plus TTS plus network, hitting 200ms end-to-end is, frankly, a fantasy for most teams. You can chase it. You can throw money at it. You can cache and prefetch and stream. At some point you bottom out. That's where perception work begins. The user can't measure your p99 latency. They can only measure how the agent feels . Those are two different problems and they have two different solutions. 5 tricks I now use to mask latency 1. Acknowledgment tokens ("Got it", "On it", "Let me check") What it is: A short, instant utterance played the mo

Originally written for bulldo.gs — republished here with the canonical link pointing home. I want to enable the V8 runtime on an existing Apps Script project so I can use modern JavaScript, but I am worried about breaking things that are already working. // appsscript.json — set runtimeVersion to enable V8 // Rollback: change V8 back to DEPRECATED_ES5 { " timeZone " : " America/New_York " , " dependencies " : {}, " exceptionLogging " : " STACKDRIVER " , " runtimeVersion " : " V8 " } // Code.gs — safe V8-compatible replacement for a common Rhino pattern // Rhino allowed: for each (var item in collection) {} // V8 requires standard for...of instead function listSheetNames () { var ss = SpreadsheetApp . getActiveSpreadsheet (); var names = []; var sheets = ss . getSheets (); for ( var i = 0 ; i < sheets . length ; i ++ ) { names . push ( sheets [ i ]. getName ()); } Logger . log ( names . join ( ' , ' )); } The one-line change and why it is a project-wide bomb Open the Apps Script editor, click Project Settings (the gear icon), and check "Show appsscript.json manifest file in editor." Then open that file and change "runtimeVersion": "DEPRECATED_ES5" to "runtimeVersion": "V8" . Save. That is the entire migration from a settings standpoint. What catches people off guard is the failure mode. V8 parses every .gs file in the project as a unit before running anything. One Rhino-only statement — a for each loop, a __iterator__ method, a Date.prototype.getYear call in an otherwise untouched utility file — causes a syntax or runtime error that prevents the whole script from initializing. Not just the file that contains the bad line. Every function, every trigger, the entire project goes dark. The first time I hit this it took me twenty minutes to figure out why a completely unrelated trigger had stopped firing. The error message pointed at the Rhino syntax in a helper file I had not touched in two years. V8 does not isolate the damage; it fails at parse time, before any executi

Originally written for bulldo.gs — republished here with the canonical link pointing home. I'm running a script that processes a large spreadsheet and it keeps dying with "Exceeded maximum execution time" before it finishes. // Checkpoint-resume pattern for long-running sheet jobs function processInBatches () { var props = PropertiesService . getScriptProperties (); var startRow = parseInt ( props . getProperty ( ' lastRow ' ) || ' 2 ' , 10 ); var sheet = SpreadsheetApp . getActiveSpreadsheet (). getActiveSheet (); var lastDataRow = sheet . getLastRow (); var BATCH = 200 ; var SAFE_MS = 5 * 60 * 1000 ; var started = Date . now (); var endRow = Math . min ( startRow + BATCH - 1 , lastDataRow ); var data = sheet . getRange ( startRow , 1 , endRow - startRow + 1 , 5 ). getValues (); for ( var i = 0 ; i < data . length ; i ++ ) { if ( Date . now () - started > SAFE_MS ) { props . setProperty ( ' lastRow ' , String ( startRow + i )); return ; } // process data[i] here } if ( endRow >= lastDataRow ) { props . deleteProperty ( ' lastRow ' ); deleteTrigger_ (); } else { props . setProperty ( ' lastRow ' , String ( endRow + 1 )); } } The 6-minute wall is per-execution, not per-task Apps Script enforces a hard 6-minute execution time limit per run, regardless of whether you're on a free account or a Workspace account (which bumps the limit to 30 minutes, but the same cliff exists). The error doesn't mean your logic is wrong; it means one continuous call to your function took too long. The fix is to stop thinking of your job as a single execution and start thinking of it as a pipeline of short runs. The first time I hit this, I wasted an afternoon trying to speed up the loop. Marginal gains didn't move the needle because the data volume was the real problem — 4,000 rows at one Sheets API call per row will always breach 6 minutes. The correct frame is: how do I save where I stopped and pick up there next run? Saving and restoring a cursor with PropertiesService PropertiesServic

Coding agents are no longer just autocomplete with a longer prompt. GitHub describes Copilot cloud agent as software that can research a repository, create an implementation plan, make code changes on a branch, run in an ephemeral GitHub Actions-powered environment, and let a developer review or create a pull request afterward. OpenAI's Codex GitHub integration similarly positions code review as a repository-aware review pass that follows AGENTS.md guidance and focuses comments on serious issues. That shift changes the buyer question. The useful question is not "does the agent usually write code?" It is "can the team detect when the agent drifts away from the developer's intent before the change reaches production?" A May 2026 arXiv paper, "How Coding Agents Fail Their Users" , gives teams a better vocabulary for that review. The authors studied 20,574 real IDE and CLI coding-agent sessions across 1,639 repositories and define misalignment as a breakdown that becomes visible through developer correction or pushback. The paper reports seven recurring symptom categories: wrong project diagnosis, misread developer intent, developer constraint violation, self-initiated overreach, faulty implementation, operational execution error, and inaccurate self-reporting. Effloow Lab also ran a bounded OpenAI API check using three synthetic, non-confidential coding-agent transcript snippets. The run did not measure real-world incidence, compare vendors, or reproduce the paper. It produced a small rubric that maps visible symptoms to review gates such as diff-scope checks, evidence-before-edit checks, acceptance-criteria coverage, and verification-output requirements. The public lab note is available at /lab-runs/coding-agent-misalignment-failure-taxonomy-poc-2026 . This guide turns that research and lab output into a practical QA checklist for teams buying, piloting, or packaging coding-agent workflows. Why This Matters for Agent Buyers Coding-agent procurement often starts with p

Originally written for bulldo.gs — republished here with the canonical link pointing home. I want to pull live JSON data from an API endpoint directly into a Google Sheet without installing an add-on. // Fetch JSON from an API and write it to the active sheet // Adjust API_URL and the field list to match your endpoint function importJsonFromApi () { var API_URL = ' https://jsonplaceholder.typicode.com/users ' ; var sheet = SpreadsheetApp . getActiveSpreadsheet (). getActiveSheet (); var response = UrlFetchApp . fetch ( API_URL ); var raw = response . getContentText (); var data = JSON . parse ( raw ); var headers = [ ' id ' , ' name ' , ' username ' , ' email ' , ' phone ' ]; var rows = data . map ( function ( obj ) { return headers . map ( function ( key ) { return obj [ key ] || '' ; }); }); sheet . clearContents (); sheet . getRange ( 1 , 1 , 1 , headers . length ). setValues ([ headers ]); sheet . getRange ( 2 , 1 , rows . length , headers . length ). setValues ( rows ); } Why getContentText() comes before JSON.parse UrlFetchApp.fetch() returns an HTTPResponse object, not a string. The first time I skipped getContentText() and passed the response object directly to JSON.parse(), it silently parsed to null and the sheet wrote nothing. You need raw = response.getContentText() to get the actual body as a string, then JSON.parse(raw) turns it into a JavaScript object or array. The URL must be publicly accessible or accept an API key via a query parameter or Authorization header. Add headers like this: UrlFetchApp.fetch(url, { headers: { Authorization: 'Bearer ' + token } }). Apps Script's UrlFetchApp quota is 20,000 calls per day on a free Google account, 100,000 on Workspace. The rectangular array constraint — why setValues fails without mapping setValues() is strict: it requires a 2D array where every row has the same number of columns. If you hand it an array of plain JSON objects, it throws 'The number of rows or columns in the range does not match the number of

Hey tech family! 👋 If you’ve noticed your favorite Chrome extensions acting a bit differently lately or if you're a developer currently sweating over a massive codebase rewrite you are experiencing the era of Manifest V3 (MV3) . 🤖 Google has officially pushed the web ecosystem forward by deprecating Manifest V2, making MV3 the absolute standard for how browser extensions behave. But why is this happening, what actually changed, and why is the internet so divided over it? Let’s break it all down in plain English! 👇 🧐 What Exactly is Manifest V3? Think of a "Manifest" as the blueprint file ( manifest.json ) that tells the browser exactly what an extension is, what files it uses, and what permissions it needs to run. Manifest V3 is Google's major architectural overhaul of this system. Its core mission sounds great on paper: improve user privacy, beef up security, and boost browser performance . However, achieving those goals meant rewriting the core rules of how extensions interact with your browser. 🛠️ The Biggest Changes & New Features MV3 isn't just a small patch; it fundamentally alters the underlying extension engine. Here are the headline shifts: Goodbye Background Pages, Hello Service Workers! 💤 In MV2, extensions used hidden, persistent background pages that ran 24/7, hogging your computer's RAM even when you weren't using them. MV3 replaces these with Service Workers. They are event-driven meaning they wake up, execute a task (like clicking an extension icon), and go right back to sleep. Hello, free RAM! 🐏 The Ad-Blocker Shakeup: webRequest vs. declarativeNetRequest 🛑 This is the most controversial change. In MV2, powerful extensions like uBlock Origin used the webRequest API to intercept, read, and block network requests in real-time using complex code. MV3 replaces the blocking version of this with declarativeNetRequest . Instead of letting the extension intercept the data, the extension must now hand Chrome a pre-defined list of rules, and Chrome does the b

Originally written for bulldo.gs — republished here with the canonical link pointing home. I have a spreadsheet of names and email addresses and I want to send each person a personalized message from my Gmail account without copy-pasting or using a paid tool. // Mail merge: Sheet cols A=Name, B=Email, C=Sent // Run from Apps Script; authorize Gmail + Sheets scopes function sendMerge () { var sheet = SpreadsheetApp . getActiveSheet (); var rows = sheet . getDataRange (). getValues (); var quota = MailApp . getRemainingDailyQuota (); var sent = 0 ; for ( var i = 1 ; i < rows . length ; i ++ ) { if ( rows [ i ][ 2 ] === ' Sent ' ) continue ; if ( sent >= quota ) { Logger . log ( ' Quota reached at row ' + ( i + 1 )); break ; } var name = rows [ i ][ 0 ]; var email = rows [ i ][ 1 ]; var subject = ' Hey ' + name + ' , here is your update ' ; var body = ' Hi ' + name + ' , \n\n Your personalized content goes here. \n\n Thanks ' ; MailApp . sendEmail ( email , subject , body ); sheet . getRange ( i + 1 , 3 ). setValue ( ' Sent ' ); sent ++ ; } } Set up your sheet and open the script editor Put names in column A, email addresses in column B, and leave column C blank — the script writes 'Sent' there as it goes. Header row in row 1 is assumed; the loop starts at index 1 (row 2) to skip it. Open the script editor from Extensions > Apps Script, paste the function, and save. The first time you run sendMerge() Google will ask you to authorize two scopes: Sheets (read/write the active spreadsheet) and Gmail (send mail on your behalf). Both are required. If you only see a Sheets prompt, delete the file and re-paste — a cached partial authorization sometimes skips the Gmail scope on older script files. Why the Sent column is the whole point Consumer Google accounts cap at roughly 100 outgoing recipients per 24-hour rolling window via MailApp. If your list has 200 rows and you run the script at 11 pm, it will send 100 and log 'Quota reached at row 101'. Without the Sent check, a sec

I've been writing about AI coding tools for months here on Dev.to. Comparisons, benchmarks, tutorials on how to squeeze the most out of Claude Code, Cursor, and the rest. And I do use them. Every single day. But last week I tried something that surprised even me. I turned them off completely. For an entire week, no AI-generated code, no autocomplete suggestions, no "explain this function" prompts. Just me, my editor, and a blinking cursor. Here's what actually happened. The First Few Days Were Rough Day one was humbling. My output dropped by maybe half. What normally took 15 minutes stretched to 40. I found myself reaching for the Cmd+K shortcut out of muscle memory half a dozen times. But somewhere around day three, something shifted. I started reading source code instead of asking for summaries. I traced through execution paths instead of having the LLM walk me through them. I caught a subtle race condition that Claude Code had confidently dismissed as "not an issue" in the same codebase two weeks prior. That moment stuck with me. The Code Was Cleaner Here's the part I didn't expect. By day five, my code was noticeably simpler. Not because an LLM optimized it, but because I actually understood the problem well enough to keep it simple. AI-generated code often over-engineers. It adds abstractions for scenarios that don't exist. It writes defensive checks for edge cases that don't apply to your use case. It looks professional but carries unnecessary complexity. When you write it yourself, you stop at the simplest working solution because you know when you're done. An LLM doesn't know when you're done. It just keeps going until the context window runs out. The Real Cost of Productivity This is the part I've been thinking about most. AI tools remove friction. That's their superpower. But friction isn't always bad. The struggle of debugging your own code is how you learn a codebase. The effort of designing an API is how you develop taste for what makes a good one. If y

“I’m not sure that this company supports a hackathon culture anymore,” one employee posted in a forum open to the entire staff.

A new report suggests the unit, which employs 6,500 people, is on the verge of revolt.

As of today, SpaceX is owned by investors who will want to see it make money.

After covering the foundational building blocks in Session 1, the next step is one of the most important problem-solving techniques in all of programming: recursion . And once recursion feels comfortable, it unlocks a powerful search strategy called backtracking . These two concepts appear everywhere in competitive programming — Fibonacci, binary search, tree traversal, merge sort, dynamic programming, N-Queens, and more. They deserve their own spotlight. 🌟 What Is Recursion? A function is recursive if it calls itself. Instead of solving a problem in one go, a recursive function breaks it into a smaller version of the same problem, solves that, and repeats — until the problem becomes simple enough to answer directly. Three things define every recursive solution: The problem is expressed in terms of a smaller instance of itself Each call reduces the problem size There is a point where the problem becomes trivial and no further calls are needed — this is the base case The Nested Box Analogy Think of recursion like opening nested boxes. A big box contains a smaller box, which contains another, and so on. Eventually you find the item you were looking for. That innermost box is the base case. Without it, you would keep opening boxes forever — which is how you get a stack overflow, not a solution. Base Case and Recursive Case Every recursive function has exactly two parts: Recursive case — the problem is reduced in size and the function calls itself again. Base case — the terminating condition. No further recursive call is made. The function returns a direct answer. Both are non-negotiable. A function without a base case will keep calling itself, consuming stack memory until the program crashes. Example: Factorial 5! = 5 × 4! 4! = 4 × 3! 3! = 3 × 2! 2! = 2 × 1! 1! = 1 ← base case Each step reduces the problem by one. When the function hits 1! = 1 , it stops, and the results unwind back up the call stack. In pseudocode: function factorial(n): if n == 1: return 1 # base cas

AI Agent Security, Malware Evasion, & LLM Data Leakage Risks Today's Highlights Today's highlights cover crucial security challenges, from sophisticated malware evasion tactics confusing analysis tools to the inherent risks of autonomous AI agents causing financial damage. We also delve into the critical data security implications of interacting with large language models, emphasizing the need for robust data governance and user education. Malware developers added nuclear and biological weapons text to to their spyware (Hacker News) Source: https://twitter.com/jsrailton/status/2064661778978533571 This report highlights a concerning tactic employed by malware developers to evade detection and analysis. By embedding seemingly innocuous, yet contextually irrelevant, strings such as "nuclear and biological weapons" text within their spyware's code or data, threat actors aim to mislead security researchers and automated analysis tools. This technique, often referred to as 'camouflage' or 'noise injection,' complicates the process of signature-based detection and behavioral analysis by adding irrelevant data that can confuse pattern matching algorithms or human analysts investigating suspicious binaries. It leverages the expectation that malicious code should contain only code related to its function, subverting this by introducing data that might trigger false positives or simply overwhelm analysis efforts. This tactic necessitates more sophisticated defensive techniques, moving beyond simple string searches or basic heuristic analysis. Organizations must enhance their sandboxing capabilities, employ advanced machine learning-driven anomaly detection, and focus on dynamic analysis that observes the actual behavior of the malware rather than relying solely on static analysis. Understanding such obfuscation and evasion tactics is crucial for developing robust threat intelligence and improving the resilience of endpoint detection and response (EDR) systems against evolving