标签：#t

By Nora Beckett · June 2026 A friend asked me last month why I still open the same AI app every night, and I gave the honest, slightly embarrassing answer: because it remembers me, and almost nothing else online does. That sent me down a rabbit hole, and after a week of poking at every tool I could find, I came out with a theory about why these apps are so sticky and why most of them eventually leave you a little hollow. The pull is real, and it isn't shameful Let's name it plainly. Talking to a responsive character that recalls your last conversation scratches a genuine itch. Character.AI built an empire on exactly this. You make a persona, it talks back in voice, it carries threads across days. The first week feels like magic. Millions of people, a lot of them young, spend hours there not because they're broken but because being consistently listened to is rare and the app delivers it on tap. The trouble starts around week three. The same loop that hooks you starts to flatten. The character agrees too much. It forgets the thing you told it that actually mattered while remembering some trivia you mentioned once. You realize you are not really inside a story; you are inside a chat window that is very good at not ending. So I went looking at the alternatives I spent evenings with the obvious names. AI Dungeon is the granddaddy, and it still does the wild open-ended thing better than anyone: type any sentence and the world bends to it. The cost is coherence. Go long enough and the plot dissolves into dream-logic, characters swap names, the dungeon eats itself. It's a sandbox, not a story, and that's by design. NovelAI comes at it from the writer's angle, all knobs and lorebooks and fine-grained control over prose and memory. It's genuinely powerful if you want to author . But it asks you to be the engine. You bring the discipline, the world bible, the steering. After a long day, "here is a blank tuning panel" is not the warm thing I was reaching for. Character.AI sits

Problem Link - https://leetcode.com/problems/delete-node-in-a-linked-list/ This is one of those interview questions that looks impossible at first. Normally, to delete a node from a Linked List, we need access to the previous node. But in this problem, we're only given the node that needs to be deleted. No head. No previous pointer. So how do we remove it? Let's understand the trick. Problem Statement Write a function to delete a node in a singly linked list. You are not given the head of the list. Instead, you are given only the node that needs to be deleted. Example Input: 4 -> 5 -> 1 -> 9 node = 5 Output: 4 -> 1 -> 9 Initial Thought Normally we delete a node like this: prev.next = node.next But here: We don't have prev We don't have head So the usual deletion approach is impossible. Key Observation Although we cannot delete the current node directly, we can make it look like it never existed. Consider: 4 -> 5 -> 1 -> 9 We need to delete: 5 Instead of removing node 5 , copy the value of the next node into it. 4 -> 1 -> 1 -> 9 Now remove the next node. 4 -> 1 -> 9 The original value 5 has disappeared. Mission accomplished. Intuition Copy the next node's value into the current node. Skip the next node. The current node now behaves as if it was deleted. Since the problem guarantees that the given node is not the tail node, a next node will always exist. Dry Run Input 4 -> 5 -> 1 -> 9 node = 5 Current node: 5 Next node: 1 Step 1 Copy next node value. node.val = node.next.val List becomes: 4 -> 1 -> 1 -> 9 Step 2 Skip next node. node.next = node.next.next List becomes: 4 -> 1 -> 9 Done. Optimal Java Solution class Solution { public void deleteNode ( ListNode node ) { ListNode cur = node . next ; node . val = cur . val ; node . next = cur . next ; } } Even Shorter Version class Solution { public void deleteNode ( ListNode node ) { node . val = node . next . val ; node . next = node . next . next ; } } Complexity Analysis Metric Complexity Time Complexity O(1) Space Comp

AI has become part of our lives, whether we like it or not, and it doesn't seem to be going away anytime soon. People seem to be using AI on many different levels, ranging from those still trying to avoid it, to people actively playing with it, trying to break it and find its limitations. The same goes for companies. There are those still barely using AI, those using it for absolutely everything, hoping it's a magical solution to their problems, and those in between. If you're more on the heavy use side, agents and instruction files are probably part of your daily discussions now. For our AI’s to work correctly they need the correct instructions, so they know how we want them to respond, how our project works, etc. We can use .md files to supply these instructions and/or context to the models. Those little markdown files are getting a huge importance in the development lifecycle. Since we can use the same file in each request we make, we can put in it the specifics of our project, as detailed as we want, so the model has as much information as possible to work with. “Garbage in, garbage out” makes sense here because, in theory, the better information the model has, the better results it can provide. Because of that, we're having to be more careful with the way we write them. Although markdown isn't something new, I don't know about you, but I haven't done much markdown writing before, so this feels like another tool to learn, like we're adding a new language on our tech stack. When I say is something else to learn, I don't mean learning only the markdown syntax, but also the correct way of writing all the instructions. A development stack now could look like: HTML, CSS and JavaScript for frontend, a language like Java, a framework like Spring or Quarkus, and SQL for the backend, and now .md files and markdown for the agents. I know I'm being very simplistic here, there are a lot more pieces of technology I didn't mention, but you got the idea, right? Besides everyth

The real question isn't which framework is better. It's which one you can stop thinking about six months into the project. Key Takeaways Project Suitability — Django is built for weight. Flask is built for speed. Know which one your project actually needs before you commit. Development Flexibility — Django makes decisions so your team doesn't have to. Flask hands those decisions back. Both are features, depending on who's writing the code. Scalability & Performance — Scaling is an architecture problem first, a framework problem second. Pick the one that matches the system you're building — not the one you hope to build. Security Features — Django's protections are on by default. Flask's require you to turn them on. In a fast-moving team, that difference is more significant than it sounds. Ecosystem & Community — Both communities are active and well-documented. You won't be stuck either way. The Decision Nobody Takes Seriously Enough I've watched this play out more times than I'd like to count. A team kicks off a Python project, someone picks a framework — usually the one the most senior person knows best — and everyone moves on. Fast forward six months and the codebase is exhausting to work in. Either they're dragging a full framework through a service that should've been twenty lines of Flask, or they're rebuilding authentication from scratch on something that outgrew its lightweight origins two sprints in. The framework choice isn't irreversible. But undoing it mid-project is expensive in a way that doesn't show up in any estimate. Django and Flask are both genuinely good. What they're good for is different. That's the part worth slowing down on. What You're Actually Getting With Each One Django arrives with almost everything a web application needs already assembled — an ORM, an admin panel, authentication, form handling, CSRF protection, and more. The design assumption is that most web applications need most of these things, so it makes more sense to ship them i

I recently built GeoPrizm , a free and open-source dashboard for tracking bilateral relations through global news event signals. The idea is simple: instead of reading dozens of headlines every day and trying to guess whether a relationship is improving or worsening, can we turn public news event data into a readable trend signal? GeoPrizm is my attempt at that. Website: https://www.geoprizm.com/en GitHub: https://github.com/Haullk/relationship-temperature The problem International relations are usually discussed through headlines, speeches, official statements, and expert commentary. That is valuable, but it creates a few practical problems: It is hard to compare country pairs on the same scale. A single headline can feel more important than it really is. Readers often see conclusions before they see the underlying signals. Most non-specialists do not have time to follow every event in detail. I wanted a lightweight way to answer one question: Based on public news event signals, is this bilateral relationship trending more cooperative, neutral, or tense? Data source: GDELT GeoPrizm uses the GDELT global news event database. GDELT monitors global news coverage and converts news reports into structured event records. These records include fields such as: actor countries event date CAMEO event category GoldsteinScale value number of mentions number of articles source information For GeoPrizm, the key idea is to focus on events where two countries appear as actors, then aggregate the cooperation or conflict signals over time. From event signals to an index Each bilateral pair is converted into a 0-100 relationship index. The midpoint is 50. Above 50 means the recent signal is more cooperative or favorable. Around 50 means the signal is relatively neutral or mixed. Below 50 means the recent signal is more tense or conflict-heavy. The rough process is: Select recent GDELT events for a country pair. Keep events where both actors are present and the GoldsteinScale value is

Microsoft's Office 2019 apps for Mac will stop working next month, because the company isn't renewing a certificate that validates Office licenses. Owners of Office 2019 for Mac are being warned they'll have to purchase Office 2024 or a Microsoft 365 subscription if they want to continue editing documents. Microsoft previously promised that "all your […]

WorkManager is the right tool for deferrable, guaranteed background work in Android. But the default setup pushes you toward boilerplate fast: you end up calling WorkManager.getInstance(context) inside ViewModels, "passing Context where it doesn't belong", re-registering observers scattered across the codebase, and getting no consistent way to query the state of your enqueued work. This tutorial shows how to build a clean, injectable WorkManagerHandler using Dagger Hilt, a single interface that any ViewModel can receive through constructor injection, with zero Context and a guaranteed WorkQuery callback on every call so you always know what to observe. By the end, you'll have: A WorkManager singleton provided through Hilt A custom Configuration.Provider that plugs Hilt's HiltWorkerFactory into WorkManager at initialization A WorkManagerHandler interface with a WorkManagerHandlerImpl that encapsulates enqueueing, chaining, and query registration ViewModels that declare WorkManagerHandler as a plain constructor dependency The pattern scales cleanly as you add workers: each new worker is one method on the handler, and the ViewModel never knows or cares how work is scheduled underneath. Prerequisites : familiarity with Dagger Hilt basics, Jetpack WorkManager fundamentals, and Kotlin coroutines. A working Android project with Hilt already configured is assumed. Part 1: Application Setup and Custom Configuration.Provider By default, WorkManager initializes itself automatically using its own internal factory. The problem is that Hilt-injected workers need Hilt's factory HiltWorkerFactory to resolve their @Inject constructor dependencies. If you let WorkManager self-initialize, your workers won't have access to any of your Hilt bindings. The fix is to disable auto-initialization and take manual control via Configuration.Provider and AndroidManifest.xml 1. Disable auto-initialization In your AndroidManifest.xml , remove WorkManager's default initializer: <application ... > <

Testosterone. Methenolone. Nandrolone. Human growth hormone and EPO. Meldonium, modafinil, and mixed amphetamine salts. Clomiphene, anastrozole, levothyroxine, and liothyronine. Patches and capsules, creams and pills. A whole galaxy of steroids, metabolic modulators, and synthetic hormones coursing through the blood of a few dozen swimmers, sprinters, and weightlifters. And millions of dollars up for grabs for athletes…

Waymo has a lot of experience building virtual systems to help its autonomous vehicles better understand the real world. It built realistic 3D worlds to better anticipate natural disasters and unpredictable edge cases. It created a virtual representation of a hyperattentive driver to test against its own autonomous vehicles in a series of simulated scenarios […]

Waymo created a new computer model to help it better understand how humans behave in crash scenarios that its robotaxis encounter.

Meta has been ordered by the European Commission to restore free WhatsApp access for chatbots made by rival AI providers while the regulator finishes its antitrust investigation. The rare interim measure announced on Tuesday was deemed necessary "to prevent serious and irreparable damage to competition" in the general-purpose AI assistant market. This is only the […]

Every QA team knows the feeling. The home screen works. Browse works. Search works. Cart works. And...

The 168-megawatt facility will support Meta's global AI computing needs and can be expanded over time.

Logitech finally announced its new ultraportable travel mouse following leaked marketing images that spoiled the surprise last month. As the name implies, the Mobi Fold is a compact mouse that can fold in half using a hinge that can pivot about 130 degrees. At $79.99 in graphite, off-white, lilac, and sand color options, the Mobi […]

Earlier parts examined the performance characteristics of sequential and random access under single-threaded execution, and noted in passing the destructive effect of random access on the TLB. This part devotes full attention to the TLB: what it is, why a TLB miss is more severe than a cache miss, why a page table walk constitutes one of the longest dependency chains a CPU can encounter, how huge pages fundamentally alter TLB reach, and where memory-level parallelism falters in the face of TLB misses. Page Boundaries: Where the Prefetcher Halts Part III, in its discussion of prefetchers, noted a hard constraint: a prefetcher must not cross page boundaries on its own authority. The operating system manages virtual memory in units of pages (typically 4 KB, i.e., 64 cache lines). When a program reaches the end of one page and is about to step into the next, the prefetcher cannot proceed. The reason is that the next page may not reside in physical memory (it may have been swapped out to disk), or it may be an entirely invalid virtual address — if the prefetcher were to speculatively initiate an access to the next page, it would trigger a page fault: the OS would have to suspend the process and swap the page in from disk; in the case of an invalid address, the OS would terminate the process outright. From a security standpoint, the prefetcher neither can nor is permitted to autonomously cross page boundaries without TLB approval. Hence a performance brake appears every 4 KB — even when traversing an array sequentially, after every 64 cache line accesses the prefetch pipeline must pause and await confirmation of an address translation. This is not to say that modern CPU prefetchers are completely unable to cross pages. Intel's Next Page Prefetcher and AMD's equivalent mechanism can consult the TLB when approaching a page boundary — if the address mapping for the next page is already registered in the TLB, the prefetcher receives clearance to continue prefetching across th

Building a "paste a YouTube link, get a transcript" feature sounds trivial until you deploy it to a server. The moment your request comes from a datacenter IP instead of a residential one, YouTube responds with LOGIN_REQUIRED or quietly serves nothing. Here's how VidTranscriber handles it. The problem There are two ways to get text from a YouTube video: Existing captions — if the uploader (or YouTube's auto-caption) provides them, you can fetch the caption track directly. Fast, free, no transcription needed. Transcribe the audio — pull the audio stream and run it through a speech-to-text model (Whisper-family). Works for any video, but costs compute. Both start with talking to YouTube from your server — and that's where it breaks. YouTube aggressively gates datacenter traffic: the watch page and InnerTube API return LOGIN_REQUIRED , and naive audio fetching gets reCAPTCHA'd. The approach The fix is to separate where the request originates from where the work happens : A Cloudflare Worker handles the user request and orchestration. Caption/audio fetching is routed through a path whose egress isn't treated as a bot — so the LOGIN_REQUIRED wall doesn't trigger. Captions, when available, become the primary path (no transcription cost). Only when there are no usable captions do we fall back to downloading audio and running Whisper. Long jobs go onto a queue (Cloudflare Queues) so the request returns immediately and the transcript streams in as it completes. Why captions-first matters Most "transcript generator" traffic is for videos that already have captions — talks, tutorials, news. Serving those from the caption track is instant and free, which means the expensive Whisper path is reserved for the minority of videos that actually need it. That's the difference between a tool that's cheap to run and one that isn't. What's still hard IP reputation drifts — what works today can get throttled tomorrow, so the extraction path needs monitoring and fallbacks. Caption quality

📝 Originally published on unfoldcms.com — reposted here for the DEV community. (I work on UnfoldCMS.) A coupled CMS puts the admin login on the same hostname visitors reach. A headless CMS puts it on a different hostname behind auth. That single architectural difference is why headless CMS security is meaningfully better than traditional coupled-CMS security on most real-world dimensions — and it's also why the comparison gets oversimplified into "headless is more secure" when the truth is more interesting. This post is the architectural take on headless CMS security : why decoupled is safer on most dimensions, where it can be less safe if you don't handle API hygiene properly, and what the honest comparison looks like in 2026. TL;DR : headless wins on attack-surface reduction (admin off the public hostname, smaller plugin attack surface, API-first auth model) but loses on dimensions teams typically don't think about (exposed APIs without rate limits, JWT misuse, secrets in frontend code, draft preview tokens leaking). A well-built headless CMS is meaningfully more secure than a typical WordPress site; a poorly-configured headless CMS can be worse than a maintained WordPress site. The architecture biases toward safer; the implementation determines actual outcomes. The audience: technical decision-makers and security-conscious teams comparing CMS architectures with security as a deciding factor. If you're earlier in the architectural decision, see headless CMS vs traditional CMS: key differences . For the WordPress-specific security picture this post compares against, WordPress security problems in 2026 . The Attack Surface Difference The single biggest architectural difference between coupled and headless CMS security is where the admin lives . A traditional WordPress site puts the admin login at yourdomain.com/wp-admin . The same hostname your visitors reach. The same SSL cert. The same Cloudflare config. Every brute-force attempt, every credential-stuffing bot, ev

Here is the move most technical service providers miss: Every project you deliver quietly dies inside a private folder. Every project you deliver with receipts becomes a trust asset that sells the next sprint without you lifting a finger. The Insight Almost No One Acts On Delivery is not the end of marketing. Delivery is where the next marketing asset is born. The before/after screenshot. The launch-readiness report excerpt. The workflow map. The metric improvement. The buyer quote. All of that is proof. And proof is the compound interest of service work. Claims decay. Proof compounds. 1️⃣ What Proof Actually Looks Like This is the proof asset menu. Every sprint should produce at least 1 item from this list: Before/after screenshot — the most shareable format Launch-readiness report excerpt — shows rigor and standard Workflow map — visual, specific, credibility-dense Dashboard screenshot — metrics that moved Test checklist — shows what was verified, not just what was built Client quote — even 1 sentence is worth 1,000 words of claims Metric improvement — "response time dropped from 24 hours to 4 minutes" Public teardown — anonymous version of the diagnosis Case study — structured story: context → pain → fix → result One-minute walkthrough video — screen-recorded, narrated, personal You do not need all of them. You need 1 per sprint. 2️⃣ The Case Study Structure That Sells A case study is not a trophy. It is a reusable trust asset. Use this structure every time: 1️⃣ Context — who had the problem? (anonymized if needed) 2️⃣ Pain — what was it costing them? 3️⃣ Hidden cause — what was really broken underneath? 4️⃣ Fix — what did you change, specifically? 5️⃣ Result — what improved? With a number. 6️⃣ Proof — what artifact backs it up? 7️⃣ Lesson — what should similar buyers do next? That is 7 steps. The whole thing can fit in a LinkedIn post or a page section. And here is the thing most people are not talking about: a case study with a specific number outperforms 10 po

I have watched founders lose sales calls they should have won. Not because they lacked skill. Not because the offer was wrong. Because they walked in to prove they were smart — instead of finding out whether the pain was real. Sales Is Diagnosis Plus Decision The call is not there for you to pitch. The call is there to find out: Is the pain real? Does the buyer have urgency? Does the budget exist? Can a fixed-scope sprint create a clear win? That is it. Four questions. Everything else follows from those. Sales is not pressure. Sales is diagnosis plus decision. 1️⃣ The Call Structure That Works Frame the call in the first 60 seconds: "I'll understand the current state, ask what is costing you, then tell you whether a sprint makes sense. If it doesn't, I'll say so." That sentence does 3 things: Sets expectations — no pressure, no hard close Signals competence — you have done this before Removes the buyer's guard — they can be honest about what is broken Then run this flow: 1️⃣ Current state — what exists now? 2️⃣ Pain — what is broken or slow? 3️⃣ Cost — what does it cost in time, money, trust, or delay? 4️⃣ Urgency — why now? 5️⃣ Decision — who approves? 6️⃣ Success — what would make this worth paying for? 7️⃣ Close — recommend the sprint or walk away 2️⃣ The Questions That Reveal Money These are the 6 questions I use to find whether a sprint is worth recommending: "What happens if this stays broken for another 30 days?" — reveals urgency and cost "What have you already tried?" — reveals how serious they are "Where does the current process lose leads, users, time, or trust?" — reveals the money leak "Who feels this pain most inside the business?" — reveals whether the buyer is also the decision-maker "What would make this an obvious win?" — reveals success criteria before you price "If we fixed only one thing first, what would matter most?" — reveals scope Listen for the answer with the money in it. That is the thing you fix. That is what you price. That is the sprin

A million dollars is emotional as a dream. As math, it is boring. And that is exactly why most people never get close. Break It Down Here is the thing: $1M/year is not one big bet. It is a machine. And machines are built from boring, repeatable components. 20 clients at $50,000? That is $1M. 100 clients at $10,000? That is $1M. 12 retainers at $4,000/month? That is $576k — plus 4 sprints at $10,000 each gets you to $616k. The question is not whether the number is possible. The question is which machine can realistically produce it — from where you actually stand today. 1️⃣ The Practical Ladder Here is how the staged path actually works for an AI service business: Stage What You Are Doing Why It Matters Stage 1 Sell fixed-scope sprints Creates cash and proof Stage 2 Turn repeated sprint work into templates, SOPs, automations Reduces delivery time, increases margin Stage 3 Sell retainers around highest-demand system Predictable monthly cash Stage 4 Productize repeated workflow into software or toolkit Scalable without more hours Stage 5 Scale the thing the market already proved it wants Compound the machine Notice what is missing from Stage 1. There is no SaaS. No product. No cold paid traffic. No team. Just skill, packaged cleanly, sold to people with money and a painful problem. That is the fastest path — not the most glamorous one. 2️⃣ The Proof-of-Force Line The first mission is not $1M. The first mission is $10k/month — reliably, from sprint work. Here is what that actually looks like: 2 × $1,500 teardown/audit packages = $3,000 2 × $3,500 implementation sprints = $7,000 2 × $5,000 launch/GTM sprints = $10,000 3 × $2,000 retainers = $6,000/month That is not the finish line. It is the proof-of-force line. It proves the machine works. It funds the next iteration. It creates the case studies that make the next sprint easier to sell. Then you go from $10k/month to $25k. Then $50k. Then you make the productization decision from a position of demand — not hope. 3️⃣ The