标签：#t

Most prompts ask AI to explain things. The best ones ask it to show you something instead. That distinction sounds cosmetic. It isn't. It changes what the model generates, how you process it, and — more importantly — whether it actually sticks. I came across this idea while watching an interview with Amanda Askell — a philosopher and researcher at Anthropic whose work sits at the intersection of AI alignment and what you might loosely call Claude's inner life. She's a primary author of the document that defines Claude's values and character — the framework that governs how the model reasons when the rules run out. Almost as an aside near the end of the interview, she mentioned a prompting technique she uses to understand complex concepts. It stopped me cold. Not because it was elaborate. Because it was disarmingly simple, and it worked in a way I hadn't thought to ask for. The Exact Prompt Template Here it is, cleaned up and ready to use: I want to understand [concept]. Please explain it by writing a fable — an indirect, narrative version of the concept. The story should embody the concept completely without naming it directly. Ideally, the reader should only start to realize what the concept actually is near the end of the story. After the fable, add a short explanation that names the concept clearly and connects it back to the key moments in the story. That's it. No elaborate scaffolding. No chain-of-thought trigger. No persona assignment. Just a deliberate decision about the order in which understanding should arrive. Why This Works (and Why Direct Explanation Often Doesn't) When you ask AI to explain a concept directly, you get a definition. Definitions are accurate and forgettable. The model produces the statistical center of everything written about that concept — clear, complete, and utterly without friction. Friction, it turns out, is how things get encoded. When a concept arrives wrapped in a story, your brain does something different. It tracks characters,

Infrastructure as Code (IaC) has revolutionized how we provision and manage cloud resources. Tools like Terraform, Pulumi, and OpenTofu allow us to define infrastructure using code, making it versionable, repeatable, and scalable. However, with great power comes great responsibility. Misconfigurations in IaC can lead to massive security breaches, such as publicly exposed data storage or overly permissive access roles. This is where Static Application Security Testing (SAST) comes in. SAST tools analyze your source code to find security vulnerabilities before the code is deployed. In this article, we'll explore how to apply SAST to a Terraform project using Checkov , a popular open-source static analysis tool for IaC, and how to automate this process using GitHub Actions. (Note: We are intentionally avoiding tfsec for this demonstration to explore other powerful alternatives). Why Checkov? Checkov, created by Bridgecrew (now part of Prisma Cloud), is a static code analysis tool for IaC. It scans cloud infrastructure provisioned using Terraform, Terraform plan, Cloudformation, Kubernetes, Dockerfile, Serverless, or ARM Templates and detects security and compliance misconfigurations. It includes hundreds of built-in policies covering security and compliance best practices for AWS, Azure, and Google Cloud. The Demo Scenario: A Vulnerable S3 Bucket Let's start by creating a simple Terraform configuration for an AWS S3 bucket. We will intentionally introduce a security misconfiguration: making the bucket public without encryption. Create a file named main.tf : # main.tf provider "aws" { region = "us-east-1" } resource "aws_s3_bucket" "my_vulnerable_bucket" { bucket = "my-company-public-data-bucket-12345" } # Misconfiguration 1: Public Read Access resource "aws_s3_bucket_acl" "example" { bucket = aws_s3_bucket . my_vulnerable_bucket . id acl = "public-read" } If we were to deploy this, anyone on the internet could read the contents of this bucket. Let's see how Checkov can

TypeScript runtime for self-organizing AI agents Discussion | Link

A few years ago, writing code was the difficult part. Today, AI can generate an API, build a React component, explain Dynamic Programming, fix bugs, and even suggest architecture—all within seconds. So here's a better question. If AI can generate code, what exactly are companies hiring humans for? The answer isn't typing speed. It isn't memorizing syntax. And it certainly isn't copying solutions faster than someone else. The value of a developer is shifting. And learning platforms need to shift with it. The Developer Role Is Changing Modern software engineering is becoming less about writing every line manually and more about making good engineering decisions. Can you understand a problem before solving it? Can you identify why one solution is better than another? Can you improve AI-generated code instead of accepting it blindly? Can you build something that is maintainable, scalable, and useful? These questions matter more today than they did five years ago. AI Reduced the Cost of Writing Code One of AI's biggest achievements is reducing repetitive work. That's a good thing. Developers spend less time writing boilerplate and more time focusing on higher-level thinking. But this creates a new challenge. When everyone has access to the same AI tools, writing code becomes less of a differentiator. Thinking becomes the differentiator. Learning Needs to Evolve Too Many learning experiences still revolve around one objective: Solve another problem. Complete another lesson. Earn another badge. Those activities still matter. But in an AI-first world, they aren't enough on their own. Learners also need opportunities to connect concepts, apply knowledge, build projects, and understand why solutions work—not just that they work. Where PyNyx Takes a Different Direction PyNyx is being built around a broader learning journey rather than a collection of isolated activities. Instead of separating learning into unrelated pieces, the platform connects multiple stages of growth. Stru

Everyone's building armies of AI "specialists" inside Claude Code. Most of them never trigger, collide with each other, and quietly bloat the very context window they were supposed to protect. I built and stress-tested 100 subagents — official built-ins, the big community collections, and a pile of my own — to find the handful that genuinely earn their keep. Here are the 12 I actually delegate to, the ones I deleted, and the uncomfortable truth about what a subagent is really for. Why I Went Down This Rabbit Hole This is the third time I've done this to myself. First it was 100 Claude Skills . Then 100 MCP servers . Now: subagents. Together they're the three pillars of the Claude Code stack — Skills give an agent competence , MCP servers give it capability , and subagents give it delegation . I'd covered two. The trilogy demanded the third. And subagents are where the hype is loudest right now. Open GitHub and you'll find collections with hundreds of them: VoltAgent's awesome-claude-code-subagents ships 154+ agents across 10 categories with 22.9k stars ; wshobson's marketplace packs 194 agents, 158 skills, and 16 orchestrators into 37.5k stars . The pitch is intoxicating: assemble a team of AI specialists — a security-auditor , a react-specialist , a kubernetes-specialist , a quant-analyst — and let Claude Code dispatch the right expert for every task. So I did the obvious thing. I installed, wired up, and actually used 100 subagents across real work: code review, debugging, test runs, security audits, database analysis, incident triage. I watched which ones Claude actually delegated to, which ones sat inert, and which ones quietly made my main conversation worse . Most got deleted. Not because they were badly written — many were excellent — but because I'd fundamentally misunderstood what a subagent is for . That misunderstanding is the whole point of this article, and I'll get to it before the list. This is the shortlist that survived. Twelve subagents. Out of a h

Most developers use Git every day and understand almost none of it. That's not an insult, it's just the reality of how most people learn tools. You pick up the commands that get you through the day, you memorize the ones that fix the situations you keep breaking, and you build a working mental model that is almost entirely wrong at the mechanical level. The mental model most people carry looks something like this: Git tracks changes to files. When you commit, it saves a snapshot of what changed. Branches are pointers to different lines of work. That's roughly correct at a surface level, but it skips over the actual machinery in a way that leaves you confused every time something unexpected happens. Why does rebasing rewrite history? Why are commits immutable? Why does detached HEAD state exist? Why can you lose work in ways that feel impossible if Git is just tracking changes? The answers are all in the object model, and the object model is surprisingly simple once you sit with it. Git is a content-addressable filesystem Before any of the version control concepts, Git is a key-value store. You put content in, you get a hash back. You use that hash later to retrieve the content. That's the entire foundation, and everything else is built on top of it. The hash Git uses is SHA-1, producing a 40-character hexadecimal string. When you run git hash-object on a file, Git takes the content, prepends a small header describing the object type and size, and runs SHA-1 over the whole thing. The resulting hash is both the key and the identity of that content. Two files with identical content will always produce the same hash. A file whose content changes even slightly will produce a completely different hash. This is the first thing that breaks people's mental models. In most storage systems, identity is location: a file is "that file" because it lives at that path. In Git's object store, identity is content. The path a file lives at is separate metadata, not the file's identity

Last month our visual-diff monitor flagged 47 changes on a client's homepage in one run. Forty-six of them were a rotating testimonial carousel that happened to land on a different slide each time the page was captured. One was real. If you've built or used any screenshot-based monitoring, you already know this problem. Two screenshots of the exact same, unchanged page rarely match pixel-for-pixel. Carousels rotate. Cookie banners fade in on a timer. Lazy-loaded images pop in a beat late. Ads shift half a pixel. Fonts render with slightly different anti-aliasing depending on what else the browser was doing. Diff two raw captures and you get a wall of "changes," and within a week nobody on the team opens the alert anymore. Why the obvious fixes don't work The first instinct is usually to loosen the pixel-diff threshold. That just trades false positives for false negatives - now a genuinely moved button or a broken layout has to clear the same bar as carousel noise, so you miss the thing you built the tool to catch in the first place. The second instinct is manual exclusion zones: tell the tool to ignore the carousel <div> , the ad slot, the cookie banner. This works until the page changes - a redesign moves the carousel, a new banner ships with a different selector, and you're back to noisy alerts plus a pile of dead config nobody remembers writing. The third "fix" is tolerating the noise, which is what most teams actually do in practice, and it's a big part of why visual regression tooling has a reputation for being more trouble than it's worth. Make the page prove it's stable before you trust anything about it The fix that actually moved the needle for us wasn't a smarter diff algorithm. It was refusing to treat a single screenshot as ground truth at all. Before any comparison happens, the page goes through a stabilization pass: known cookie/consent overlays get removed (we track a couple hundred variants at this point — cookie banner vendors are not standardized),

This is The Stepback, a weekly newsletter breaking down one essential story from the tech world. For more on the bleak state of the video game industry, follow Andrew Webster. The Stepback arrives in our subscribers' inboxes on Sunday at 8AM ET. Opt in for The Stepback here. How it started Microsoft closed out Summer […]

Chemicals from accidents that injured or killed people increased by nearly 50 percent in recent years.

Don’t suffer the buffer. These WIRED-tested home routers will deliver reliable internet across your home, whatever your needs or budget.

Wildfire survivors call fire-prediction markets “morally reprehensible” and worry they could increase the risk of arson.

The heat of the Hadean may have come from impacts as well as the interior.

This massive 85-inch model is highly customizable but jaw-droppingly expensive.

Eight Sleep’s Pod 5 is great at its job, but its job is also watching you sleep.

A large-scale clinical trial has shown that even long-term consumption of DHA—an omega-3 fatty acid found in abundance in oily fish—may not lead to improvements in cognitive function.

Your order-processing Lambda starts sending duplicate confirmation emails. Not always — maybe one order in twenty. CloudWatch shows more invocations than messages published. The function code hasn't changed in weeks. What changed is that someone added a fraud check that pushed processing time from 25 seconds to around 45, and your SQS queue is still running the default 30-second visibility timeout. That combination is the whole bug. When a Lambda pulls a message from SQS, the message isn't deleted — it's hidden for the duration of the visibility timeout. If the function is still working when that window closes, SQS assumes the consumer died and hands the same message to another invocation. Now two Lambdas are processing the same order, both will "succeed," and both will send the email. Nothing errors. Nothing retries. There is no log line that says "this message was delivered twice because your timeouts are misconfigured." Infrawise ( npm ) flags this exact mismatch as a high-severity finding before it costs you an afternoon of staring at idempotency-free handler code. This post walks through why the bug is so hard to see, how the detection works, and how to keep an AI assistant from reintroducing it. Why you never catch this one yourself Three things make this misconfiguration nearly invisible: It passes every test. In local tests and staging, your handler processes a synthetic message in two seconds. The 30-second visibility window never comes close to expiring. The bug only exists under production conditions — real payload sizes, real downstream latency, cold starts stacking on top of slow dependencies. The defaults set the trap. SQS queues default to a 30-second visibility timeout. Lambda functions routinely get their timeout bumped to 60, 120, or 900 seconds as they grow. Nobody bumps the queue at the same time, because the two settings live in different consoles, different IaC resources, and usually different pull requests. The failure signature points elsewhe

A new study has succeeded in mapping, on a global scale, the fungal network that supports plant life and helps regulate our planet’s climate.

Hello, everyone. When listening to a conversation, we naturally keep track of who is speaking. A program has a harder job: beyond finding speech, it must also determine where one speaker gives way to another. Today, I will use an ONNX version of Pyannote Segmentation 3.0 to detect speaker changes in a two-person conversation and split the recording into one WAV file per utterance. What I Tested This lab uses FFmpeg to decode a roughly 14-second conversation into a 16 kHz mono waveform. It then combines the Pyannote segmentation model with simple post-processing to produce contiguous speaker segments. I wanted to verify: Whether six alternating utterances can be separated into six segments Whether the detected speaker indexes remain consistent throughout the recording Whether ONNX Runtime can process the audio faster than real time using only its CPU execution provider Whether every segment can be saved as a separate WAV file The complete code and reproducible environment are available in the pyannote-scd lab in kiarina/labs . This test performs segmentation using the model's speaker indexes. It does not compare speaker embeddings or run clustering, so it is not a complete speaker diarization pipeline that identifies the same person throughout a long recording. Reproducing the Lab You will need: mise uv FFmpeg curl The following commands fetch only this lab, download the shared test audio, and run it: git clone --depth 1 --filter = blob:none --sparse \ https://github.com/kiarina/labs.git cd labs git sparse-checkout set .gitignore .mise/tasks Makefile mise.toml \ 2026/07/04/pyannote-scd make download-test-assets mise -C 2026/07/04/pyannote-scd run On the first run, the task downloads the full-precision onnx/model.onnx file from onnx-community/pyannote-segmentation-3.0 on Hugging Face. uv then prepares the Python dependencies and runs the detector. How Speaker Segments Are Detected The input is this shared test asset: assets/mp3/conversation_2speaker_14s_16k.mp3 The re

🧠 Building CogneeCode - AI Developer Memory Assistant The Problem Every developer faces the problem of lost context. "Why did I make this decision 3 months ago?" "How did I fix this bug last week?" Current AI tools forget everything between sessions. This is a real problem that wastes hours of developer time. My Solution CogneeCode is an AI developer memory assistant that builds a permanent knowledge graph using Cognee Cloud . It remembers every decision, bug fix, and code context you give it. What It Does ✅ Log architectural decisions with tags and context ✅ Log bug fixes with error messages and solutions ✅ Ask natural language questions about your codebase ✅ Get answers with evidence citations from the knowledge graph ✅ Semantic search across all memories ✅ Visual timeline of all decisions and bug fixes ✅ Analytics dashboard showing memory insights ✅ Knowledge graph visualization Tech Stack Backend: Flask (Python) Memory Layer: Cognee Cloud LLM: Groq Llama 3.3 Frontend: Vanilla HTML + CSS + JS Icons: Tabler Icons Cognee Cloud APIs Used remember() - Save decisions and bug fixes with metadata recall() - Natural language queries with evidence citations search() - Semantic search across memories visualize() - Knowledge graph visualization improve() - Memory graph enrichment forget() - Remove outdated memories Why This Matters When you return to a project after months, all your reasoning and solutions are still there, searchable in natural language. No more "Why did I do this?" or "How did I fix this bug?" Demo Watch the video: https://youtu.be/TNcBIBuPW7c Links 🔗 GitHub: https://github.com/JOSESAMUEL14/cogneecode 🔗 Live Demo: https://josesamuel.pythonanywhere.com AI Assistance Disclosure Built with assistance from Claude and Gemini AI. Built for WeMakeDevs x Cognee Hackathon 2026 Category: Best Use of Cognee Cloud ⭐ Star the repo if you find it useful!

You did the hard part. You designed it, you built it, you shipped it. The product is good. And still, the users do not come. I have been in that exact spot more than once. You refresh the analytics, you tell yourself it is early, and quietly a worse question starts to form: what if people are not ignoring my app, what if they simply never see it? Here is the thing almost nobody tells builders in 2026. For a growing share of your future users, the front door to the internet is no longer a list of blue links. It is a sentence. Someone opens ChatGPT, Perplexity, or Google's AI Mode and types "what is the best tool for X." The model replies with a short list of names. If your product is not one of them, you do not exist in that moment. There is no page two to claw your way onto. There is one answer, and you are either in it or you are not. Three things are probably true about your app right now, and you cannot see any of them Your app might render blank to the machines that decide. If you built a single-page app (React, Vue, most modern stacks), the raw HTML a crawler receives can be an almost empty . Most AI crawlers do not run JavaScript. They read what your server sends and leave. To them, your beautiful app has no words, no product, no reason to be cited. You can rank number one on Google and still be missing from the answer. In one large 2025 study, roughly 68 percent of the pages cited in AI Overviews were not even in the top ten organic results. Ranking and being cited have quietly become two different games. Winning the old one no longer wins you the new one. A model may already be describing your product to strangers, and getting it wrong. A feature you do not have. A price that is out of date. A category that is not yours. You are being represented in rooms you will never enter, by a narrator you never hired, and the only way to fix the story is to give the machines a cleaner one to read. None of this shows up in your dashboard. That is what makes it dangerous