AI 资讯

The Department of Justice says that federal employees can now download TikTok on their government devices.

There is a note in my runbooks that says the Enter key works. That is almost the whole note. Press Enter and the prompt submits. I wrote it in bold, with sources and a date, because one of my AI agents once fixed the Enter key. The fix was the bug. The Fix Was the Bug I run a fleet of Claude Code agents in tmux panes. An orchestrator script types a prompt into a pane and presses Enter for it. One day an agent decided the submissions were not going through, and it knew the fix: send a backslash before the Enter. That sounds plausible if you have ever fought a terminal. It is also exactly backwards. In Claude Code, backslash plus Enter inserts a newline. It is the multiline key. So the fix turned every prompt into a draft that quietly grew longer and never sent. The panes looked busy. Nothing was happening. The submissions had been fine all along. The agent just had not waited for the reply. What broke: An agent changed Enter to backslash-Enter to repair prompt submission. Backslash-Enter creates a newline, so the repair silently stopped every prompt from sending. The system it fixed had never been broken. There is a second note in the same genre. My monitoring dashboard answers its health check with a 302 redirect to the login page. That is what healthy looks like there. But a 302 looks like trouble if you are hunting for outages, and agents kept trying to repair it. So the runbook now says, more or less: the redirect is normal, do not fix the healthy system. Human teams do not write notes like these. Nobody pins "the Enter key works" to the wall of an office. A New Hire Every Session Why did I have to? Because a human hits a dead end once. The wince is the documentation. Whoever broke a build by fixing the Enter key would remember it for years, tell the story at lunch, and the whole team would absorb it without anyone writing a word. An agent has none of that. It has no episodic memory. Every fresh context window is a new hire: smart, fast, and seeing your system fo

Recap. Part 1 framed the supervision problem. Part 2 architected the four-model system on AWS and counted the hardware. Part 3 put the gate on the page in fifteen lines of PyTorch. Now the question that decides whether any of it mattered: does the gate actually earn its keep - and what would it cost to know? This is the close. A verification design, the stability instrumentation that separates a real evaluation from a lucky one, and the FinOps reality that is the reason this whole series is a blueprint instead of a benchmark. SDAR makes two claims, not one It's tempting to reduce the paper to a single number. The reported gains over plain GRPO are real and worth stating - their numbers, not mine : roughly +9.4% on ALFWorld, +7.0% on Search-QA, +10.2% on WebShop accuracy. But the headline percentage is the less interesting claim. The one that matters is the second: SDAR avoids the training instability that naive GRPO+OPSD falls into . The whole point of the gate Part 3 was to keep the teacher's noisy rejections from destabilizing training. So a verification that only measures final task success has tested half the paper. You have to measure stability too - and most reproductions don't. That two-pronged claim dictates the experiment. The verification: three arms, not two You cannot prove SDAR's thesis with a before/after. You need three training runs, identical except for the supervision: Arm What it is What it proves A. GRPO Plain agentic RL, no teacher The baseline the +9.4% is measured against B. Naive GRPO+OPSD Teacher distillation, no gate The instability SDAR claims to fix C. SDAR Gated distillation Part 3 Beats A on score and beats B on stability Drop arm B and you can show SDAR beats GRPO, but you've quietly deleted the paper's actual contribution - there's no evidence the gate did anything a plain teacher wouldn't. Arm B is the expensive arm nobody wants to run and the one that makes the result credible. Metrics that actually test the claim Metric What it mea

I’ve read the word “encrypted” on more apps than I can count, and most of the time it tells you almost nothing. Here’s what it really means, the way I’d explain it to a friend. Every app you use will tell you your data is encrypted. It’s on the login screen, the pricing page, the little padlock in the corner of the browser. And because it’s on everything, it’s stopped meaning much. I’ve spent more time on that one word than I’d care to admit, building a notes app where it actually has to be true, so here’s how I think about it. No maths. No padlock pictures. Underneath, encryption is an old and simple idea. You take a message, turn it into nonsense nobody can read, and make sure only the right person can turn it back. That’s the lot. Everything after that is detail about how good the nonsense is, and who’s allowed to undo it. The whole thing in one sentence Encryption takes something readable and mixes it into a mess that means nothing on its own. A matching key turns the mess back into the original. No key, and the mess stays a mess. The readable version is called plain-text. The mixed version is called cipher-text. That’s the entire vocabulary you need to know. Encryption turns plain-text into cipher-text, decryption is turning it back. A note is just text until you scramble it Say you’ve got a note on your phone, “dentist Thursday, 3pm”. Stored as it is, anyone who gets at the file reads it straight off. A thief with your unlocked phone. An app you handed too many permissions to. A company keeping a copy on its servers. All of them see “dentist Thursday, 3pm”. Encrypt it and that same note might sit on the disk as 9f2ac1b0e7..., a run of characters that means nothing. The appointment is still in there, in the sense that the right key brings it back, but on its own it tells a snoop nothing. Not the time, not the day, not that it was ever about a dentist. People reach for a padlock to explain this and I’ve never liked it. A padlock just stops you getting to the thi

Every engineer eventually hits this phase: “My design looks okay… but something feels off.” No compile errors. No obvious bugs. But still: responsibilities feel scattered services feel too big entities feel too thin logic feels duplicated boundaries feel unclear This is normal. Because domain modeling is not about getting it right in one attempt. It is about refining structure until the business behavior becomes clear. Step 1 — Start With the Symptom, Not the Code If your design feels wrong, don’t immediately rewrite everything. First identify the symptom: Common symptoms: too many “Manager” services logic repeated in multiple places unclear ownership of rules too many dependencies between modules frequent “if-else explosion” Each symptom points to a specific modeling issue. Step 2 — Check If Invariants Are Scattered Ask: “Where are my business rules living?” Bad sign: Rules inside services + controllers + helpers This leads to: inconsistent behavior duplicated validation broken business guarantees Good design: invariants live close to the entity or aggregate root Step 3 — Check Entity vs Service Confusion A very common issue: Entities become dumb: only fields no behavior Services become overloaded: all logic all rules all decisions This creates: Anemic Domain Model + Fat Services Fix mindset: Entity = owns behavior + protects state Service = coordinates workflows Step 4 — Check Your Aggregate Boundaries Ask: “What must stay consistent together?” If your answer is unclear, you likely have: wrong aggregates or missing aggregates Example problem: Cart and Order sharing logic This causes: inconsistent pricing unclear lifecycle ownership Fix: Cart = intent Order = truth Step 5 — Look for “Hidden Coupling” Hidden coupling happens when: one module depends on internal state of another multiple services modify same data business rules are duplicated across boundaries This leads to fragile systems. Strong design ensures: each domain owns its own truth. Step 6 — Validate Stat

Most A/B testing happens in the browser: a script swaps a headline or button color after the page loads. That works for surface-level UI changes, but it cannot test the logic that runs before a page is ever rendered — a pricing algorithm, a search ranking model, a checkout flow, or a backend API response. Server-side A/B testing moves the experiment decision into your application code, where you control the full request lifecycle. This guide explains when to test server-side, how it differs from client-side testing, and how to implement it with Optimizely Feature Experimentation, including working SDK code for Node.js and Python. What Server-Side A/B Testing Is In a server-side A/B test, your application server decides which variation a user sees and renders the response accordingly. Instead of shipping the control experience and patching it in the browser, the server already knows the assignment by the time it builds the HTML, the JSON payload, or the rendered component. The decision is deterministic: a given user ID is consistently bucketed into the same variation, so the experience stays stable across requests and devices. Your code branches on that assignment, serves the corresponding experience, and reports a conversion event when the user does something that matters — a purchase, a signup, a search that returns a click. This is the model Optimizely calls Feature Experimentation . If you have used Optimizely before, you may know this product by its former name, Full Stack — the SDKs, datafile, and decision model are the same lineage, now under the Feature Experimentation name. Searchers still look for "Optimizely full stack," but the current product and documentation use Feature Experimentation. When to Test Server-Side Server-side testing is the right tool when the thing you are changing is not a cosmetic, post-render tweak. Reach for it in these situations: Backend logic and algorithms. Recommendation engines, search ranking, fraud scoring, feed ordering, and

Most AI assistants forget everything after each session. Memoria remembers, forgets, and evolves—extracting personal facts, resolving contradictions, and reflecting on what it knows. This post shares the journey of building a production‑ready MemoryAgent for the Qwen Cloud Hackathon, Track 1 . Inspiration Every conversation with a typical chatbot starts from zero. You tell it you're allergic to peanuts on Monday, and by Wednesday it recommends pad thai with crushed peanuts. The model doesn't forget; it never had long‑term memory in the first place. Without durable knowledge about who you are, real personalisation is impossible. We built Memoria to solve that problem: a personal AI with human‑like memory that remembers what matters, forgets what fades, resolves contradictions, and evolves its understanding of you over time. Real memory isn't a bigger context window—it's extraction, prioritisation, decay, consolidation, and reflection. The hackathon challenged us to deliver a memory‑efficient, production‑grade MemoryAgent, and we built one from the ground up on Alibaba Cloud. What Memoria does Memoria organises knowledge in three deliberate tiers: Session Memory (Redis) – the last 10 messages of the active chat. Personal Memory (PostgreSQL 16 + pgvector) – user‑centric facts embedded with text-embedding-v3 , ranked by hybrid scoring, and subject to decay, consolidation, and conflict resolution. Context Archive – full transcripts stored for on‑demand search, never polluting routine retrieval. Other key features: Autonomous memory lifecycle : daily decay, weekly consolidation, and background reflection. Personal Intelligence toggle : global memory access vs. session‑only. Memory‑Less incognito mode : no memory reads or writes. MCP skills server : exposes get_core_memories , get_user_preferences , forget_memory , and strengthen_memory to any Qwen agent. Conflict detection & versioning : contradictory facts are automatically flagged and superseded. Persona customisation :

Over the past few months I built a side project that taught me more about production system design than any course. A Slack bot for deploy queue management. This isn't about the business side of it, it's a technical breakdown of the architecture decisions, the real problems I hit building a Slack app with NestJS, and what I learned solving each one. The problem Every engineering team has lived this. Two people deploy at the same time, one overwrites the other, and it turns into "who's touching prod right now?" shouted into a Slack channel. Sounds simple. Solving it properly across multiple teams, multiple environments, with timeouts, without ever locking anyone out, is not. Stack and why NestJS + TypeScript on the backend, PostgreSQL via Prisma, Redis + BullMQ for background jobs, @slack/bolt for the Slack integration. Choosing NestJS wasn't just preference. Its modular architecture (modules, providers, guards, interceptors) mapped really well to the domain. Every entity (Workspace, Project, Environment, Queue) became its own module, with the repository pattern keeping Prisma out of the business logic layer. The hardest problem: dynamic modals in Slack Block Kit Slack's Block Kit doesn't natively support a select input that reloads its options based on another select's value, within the same form. If you want "pick a project, then load that project's environments," there's no built-in prop for that. The solution combines two Bolt event types. A block_actions listener on the project select fetches the environments, then re-renders the whole modal via views.update : app . action ( ' project_select ' , async ({ ack , body , client }) => { await ack (); const selectedProjectId = body . actions [ 0 ]. selected_option . value ; const environments = await environmentService . findByProject ( selectedProjectId ); await client . views . update ({ view_id : body . view . id , view : buildModalWithEnvironments ( environments ), }); }); The detail that tripped me up the most: t

If your team has ever spent 20 minutes on a pull request arguing about brace placement instead of the actual bug, welcome to the club. StyleCop was the tool to keep C# codebases from turning into everyone's personal-style soup. It did its job. But it's also old, slow, and wasn't built for a world where half your codebase might be vibe coded. The good news: .NET now ships with everything you need to enforce style natively, faster, and without an extra NuGet package. This post walks through why the old approach creaks under modern workloads, and gives you a copy-pasteable migration plan to fix it. Table of Contents The Real Cost of Style Debates Quick Refresher: What Is StyleCop? Do We Even Need Linters Now That AI Writes Code? The Problem With StyleCop: It's Slow The Modern Toolbox The 3 Layer Guardrail Strategy Step by Step Migration Guide Before and After Seeing It In Action Key Takeaways Wrapping Up The Real Cost of Style Debates Nobody has ever gotten a promotion for winning a tabs-vs-spaces argument. Yet these debates eat real time: PR bikeshedding ,reviewers nitpick spacing instead of catching actual logic bugs. Noisy git diffs ,one developer's auto-formatter touches 300 lines to fix a 3-line bug. Cognitive overhead ,jumping between services that each "feel" different slows everyone down. A linter's whole job is to make these arguments boring and automatic, so humans can focus on things that actually matter,like whether the code works . Quick Refresher: What Is StyleCop? StyleCop (and its Roslyn-based version, StyleCop.Analyzers ) is a static analysis tool that checks the visual grammar of your C# code,not bugs, not security holes, just style: Are public members documented? Are namespaces organized consistently? Do braces follow the "approved" pattern? It's not checking if your code is correct . It's checking if your code looks correct. Do We Even Need Linters Now That AI Writes Code? Short answer: yes, more than ever. AI coding assistants (Copilot, Cursor, and

WordPress affiche une page blanche, un 403, ou la boucle de connexion infinie sur /wp-admin : voici le protocole de diagnostic que nous utilisons, dans l'ordre, avec les commandes exactes. 1. Identifier le type de blocage Trois familles de symptômes, trois causes différentes : 403 Forbidden : règle serveur ( .htaccess , WAF, IP bannie) ou cookies corrompus Boucle de redirection login : problème de cookies/HTTPS mal déclaré ( WP_HOME / WP_SITEURL ) Page blanche (WSOD) : erreur PHP fatale, souvent une extension ou le thème 2. Le fix express des cookies (cause n°1 du 403) Avant de toucher au serveur, videz les cookies du domaine et testez en navigation privée. Si ça passe en privé, c'est un cookie corrompu — pas le serveur. Le détail complet du mécanisme est dans notre guide WordPress erreur 403 et cookies bloqués . 3. Désactiver les extensions sans wp-admin # Via WP-CLI (le plus propre) wp plugin deactivate --all # Sans WP-CLI : renommer le dossier mv wp-content/plugins wp-content/plugins.off Si wp-admin revient, réactivez une par une pour isoler la coupable. 4. Vérifier .htaccess et les règles serveur Un .htaccess corrompu ou une règle de sécurité trop stricte bloque l'accès admin. Régénérez un fichier propre (Réglages → Permaliens, ou à la main). Pour générer des règles saines — protection wp-login, anti-hotlink, cache navigateur — sans risquer la syntaxe, nous maintenons un générateur de .htaccess WordPress gratuit . 5. Purger tous les caches (souvent oublié) Un cache de page qui sert une vieille version de wp-login provoque des boucles incompréhensibles. Purgez dans l'ordre : cache navigateur, cache de page (extension), cache serveur (LiteSpeed/Varnish), OPcache. La méthode complète par type de cache : comment vider le cache WordPress . 6. Le guide complet Chaque étape ci-dessus est développée (avec les cas 404 wp-admin, erreur critique, mot de passe perdu via WP-CLI et phpMyAdmin) dans notre guide de référence : accéder à wp-admin : connexion et administration Wo

A few months ago, I was searching for a backend engineering job. Every day looked the same: Open LinkedIn Open Naukri Search for Python jobs Open dozens of tabs Read every job description Apply Repeat The frustrating part wasn't finding jobs. It was finding the right jobs . I kept getting recommendations for roles that technically matched my resume because they contained words like Python , Backend , or API , but after reading the description I'd realize they wanted a completely different skill set. I started wondering: Why are job boards still matching keywords instead of understanding what a developer actually knows? That question eventually turned into a side project called Jobspiq . The Problem Imagine these two jobs: Job A Python FastAPI PostgreSQL Redis Job B Java Spring Boot Oracle Kafka Both are "Backend Engineer" roles. A keyword-based system often treats them as similar. As developers, we know they're not. What I Built Instead of matching keywords, I built a system that compares a developer's profile with a job description to understand how well they actually fit. The platform: Collects jobs from multiple sources. Removes duplicate postings. Scores every job based on how closely it matches your profile. Sends alerts only for high-quality matches. Helps track applications in one place. The goal isn't to show more jobs. It's to show fewer, better ones. What I Learned Building the product taught me something interesting. Writing the software was the easier part. Helping people discover it is much harder. That's why I'm starting to build in public and share what I'm learning along the way. If you've ever built search systems, recommendation engines, or developer tools, I'd love to hear your thoughts. You can check out the project here: https://jobspiq.in Feedback is always welcome.

I've been building a level editor for Quake 3 that runs entirely in the browser: Radiant-style layout, brush and patch editing, CSG, terrain sculpting, and entity editing. It opens and saves .map file and you can play the maps you build directly in the browser using a webassembly build of ioquake3.

A 360-degree camera is a great way to ensure you capture every bit of the action, but prices tend to be on the high end for models worth your attention. That’s why it’s notable that the GoPro Max 2 accessory bundle is discounted to $369 at Amazon (a dollar more at Best Buy and GoPro). […]

Some of my kitchen appliances are LG and I installed the LG ThinQ app on my phone. Sometimes I like to leave a cold dish in the oven before I go out then remotely start it when I’m on my way back home, so I arrive to a nice hot dinner. After a recent HN post about LG malware and further research, I decided to kick my appliances out of the network. I also tried to remove my user account just to find out that in order to use the app I need to first accept the new terms of use. I asked ChatGPT for

Now generally available, Pinecone Nexus is a "knowledge engine" for AI agents that transforms enterprise data into a structured layer agents can query directly. It enables teams to ingest and curate business context once for all, making it reusable across agents and reducing token costs while improving accuracy. By Sergio De Simone

TL;DR: Turn hours of raw GoPro footage + a .fit file into a 60-second highlight reel with ride telemetry burned in. Every second of the ride is scanned by gemini-3.5-flash, as is the clip ranking + curation. The whole thing costs about $0.04 per ride and takes 10 minutes. Longer version: Road cycling has been my primary form of exercise, social outlet, therapy, wardrobe expense, and personality trait for almost a decade. I ride most weekends, usually out of Manhattan and up 9W. By the end of a r

I run a scheduled agent that writes and publishes DEV.to articles twice a day. Step 5 of its instructions has always said the same thing: write the log entry, commit the drafts, push. I've read that line a dozen times without questioning it. This morning I actually checked what "commit the drafts" had been doing for the last month, across more than thirty published articles. The answer: nothing. Not once. the check that should have happened on day one The task instructions reference source files like drafts/scheduled-agent-shared-quota-no-memory.md and drafts/one-env-key-two-usernames.md in every log entry — real filenames, written by the agent, presumably sitting in the repo as a record of what was drafted before it got published. I went looking for one of them: $ git log --all -- drafts/ $ # (nothing) Empty. Not "one commit, then deleted later" — completely absent from git history since the very first commit in this repo. Every single run that logged "committed drafts + the log" had, in fact, only ever committed the log. why git let this happen silently .gitignore in this repo has listed drafts/ since the initial commit: . env __ pycache__ / *. pyc codes / drafts / . omc / . claude / CLAUDE . md That line predates the scheduled publishing task entirely — it was almost certainly written back when drafts were just scratch files someone edited by hand before a publish script existed. Nobody revisited it when the publishing task's instructions later started saying "commit the drafts." The instruction and the ignore rule have been quietly contradicting each other since before either was written by the same person in the same sitting. Here's what actually happens when a script (or an agent) runs git add drafts/whatever.md in this repo: $ git add drafts/gitignore-ate-my-drafts-folder.md The following paths are ignored by one of your .gitignore files: drafts hint: Use -f if you really want to add them. hint: Turn this message off by running hint: "git config advice.addIgn