标签：#ia

How we tackled 精准翻译与语言识别 (precise translation and language identification) for AI-powered book translation. The Problem: Garbage In, Garbage Out When we first launched LectuLibre, our AI book translation service, we thought the hardest part would be fine-tuning LLM prompts for literary quality. But we quickly discovered a more fundamental hurdle: if the source language of an uploaded book is misidentified, no amount of prompt engineering can salvage the translation. Users upload EPUBs and PDFs from all over the world. Some contain metadata specifying the language, but many don't. Others are multilingual books, or have prefaces in a different language. Our initial language detection using Python's langdetect library was correct only about 85% of the time on real-world uploads. That 15% error rate meant entirely garbled translations, frustrated users, and wasted LLM API credits. We needed something far more robust—what we internally call 精准翻译与语言识别 (precise translation and language identification). Here’s how we built it. The Language Detection Pipeline: From 85% to 98% Accuracy Our first instinct was to try heavier models like fastText's pre-trained language identification model, which is known for high accuracy. But when we tested it on book excerpts, we hit a new problem: short paragraphs or dialogues in one language embedded in a book of another language (e.g., French phrases in an English novel) would throw off chunk-level detection. We realized that we needed a two-tier approach: book-level language detection with confidence scoring, and per-chunk verification before translation. Combining Multiple Detectors with Voting We created a LanguageDetector class that runs several detectors and picks the majority vote, with a fallback to user-specified language when available. The detectors we use are: fastText with the official lid.176.bin model (loaded once, not per request) langdetect , which is lightweight and good for long texts cld3 (Compact Language Detector 3) fr

In my previous post, Monitoring Claude Code hook watchdogs with launchd , I set up liveness monitoring for hooks — and immediately ran into the next question: a healthy hook means nothing if the product behind it is down. What I really wanted was a single page I could skim in five minutes every morning and know that everything is fine. That page is daily-brief.sh . launchd runs it three times a day (8:00, 10:30, and at login), and it compiles production HTTP probes, hook latency p95, launchd exit codes, 7-day API costs broken down by model, and per-project git status into one Markdown file appended to Obsidian. The problem: checking five places by hand every morning The more you automate, the higher the risk that something breaks silently. I used to open all of these manually every morning: The Vercel dashboard (production liveness) launchctl logs (scheduled job failures) Claude Code cost usage git status for each project The hook latency JSONL Just opening them took 3–5 minutes. Two incidents slipped through unnoticed (2026-06-11: GitHub Scout silently going blank, and a server configuration error in the autolike license API). Consolidating everything into one automatically delivered page makes missing things physically impossible. Overall design: 3 triggers → 1 Markdown file → append to Obsidian launchd ├─ StartCalendarInterval: 8:00 ├─ StartCalendarInterval: 10:30 └─ RunAtLoad: true（ログイン時） ↓ ~/.claude/scripts/daily-brief.sh ↓ ~/.claude/logs/daily-brief-YYYYMMDD.md ← 正本ログ ~/.claude/logs/daily-brief-latest.md ← 最新コピー ~/Desktop/Daily Brief/today-brief-YYYYMMDD.md ~/Documents/claude-obsidian/wiki/briefs/daily/today-brief-YYYYMMDD.md Even when the second run fires at 10:30, the marker <!-- daily-brief YYYYMMDD --> prevents duplicate appends (details below). The script opens like this: #!/usr/bin/env bash # launchd で毎日 8:00 / 10:30 / ログイン時 実行（再実行してもマーカーで二重追記しない）。 # 注意: Desktop / ~/Documents(vault) は TCC 保護領域 → plist は /bin/bash 直起動（FDA付与済み）。 # /bin/zsh 経由だと FDA 未付与で書き込

If your app sends email — transactional or marketing — three DNS records decide whether it lands in the inbox or the spam folder: SPF , DKIM , and DMARC . Here's how to look them up and sanity-check them in Python, no third-party API required. Install the one dependency: pip install dnspython SPF: who is allowed to send SPF lives in a TXT record on the domain itself and starts with v=spf1 . import dns.resolver def get_spf ( domain ): for rec in dns . resolver . resolve ( domain , " TXT " ): txt = b "" . join ( rec . strings ). decode () if txt . startswith ( " v=spf1 " ): return txt return None print ( get_spf ( " github.com " )) # v=spf1 ip4:... include:_spf.google.com ~all A quick gotcha worth checking: SPF allows at most 10 DNS-querying mechanisms ( include , a , mx , ptr , exists , redirect ). Go over and receivers return permerror , which quietly breaks authentication: def spf_lookup_count ( spf ): return sum ( spf . count ( m ) for m in ( " include: " , " a: " , " mx: " , " ptr " , " exists: " , " redirect= " )) spf = get_spf ( " example.com " ) if spf and spf_lookup_count ( spf ) > 10 : print ( " ⚠️ SPF exceeds the 10-lookup limit " ) DMARC: the policy that ties it together DMARC is a TXT record on the _dmarc. subdomain and starts with v=DMARC1 . def get_dmarc ( domain ): try : for rec in dns . resolver . resolve ( f " _dmarc. { domain } " , " TXT " ): txt = b "" . join ( rec . strings ). decode () if txt . startswith ( " v=DMARC1 " ): return dict ( kv . strip (). split ( " = " , 1 ) for kv in txt . split ( " ; " ) if " = " in kv ) except dns . resolver . NXDOMAIN : return None print ( get_dmarc ( " github.com " )) # {'v': 'DMARC1', 'p': 'reject', 'rua': 'mailto:...'} The key field is p : none (monitor only), quarantine (spam folder), or reject (bounce). If a domain sends real mail but has p=none , it's not protected against spoofing yet. DKIM: the signature key DKIM is trickier because you need the selector — a label chosen by the sender that lives at SELECT

When you scrape at any real volume, the bottleneck is rarely your code — it's the target site's rate limiting and IP bans. Rotating residential proxies solve this by routing each request through a different real-user IP. Here's how to wire them into requests and Scrapy in Python, including the sticky-session trick most tutorials skip. The proxy URL format A residential proxy is just an authenticated HTTP/SOCKS endpoint. With a pool gateway, you target a country and control session behavior through the username , not separate endpoints: http://USERNAME_country-us_session-a1b2c3_lifetime-30:PASSWORD@proxy.gproxy.net:1000 country-us — exit country (ISO code) session-a1b2c3 — a sticky-session id; reuse it to keep the same IP , change it to rotate lifetime-30 — how many minutes that session's IP stays fixed Basic request through a rotating proxy import requests USER = " USERNAME " PWD = " PASSWORD " def proxy ( country = " us " , session = None , lifetime = 30 ): tag = f " _country- { country } " if session : tag += f " _session- { session } _lifetime- { lifetime } " url = f " http:// { USER }{ tag } : { PWD } @proxy.gproxy.net:1000 " return { " http " : url , " https " : url } # New IP on every call (no session id): r = requests . get ( " https://api.ipify.org?format=json " , proxies = proxy (), timeout = 30 ) print ( r . json ()[ " ip " ]) Run it in a loop and you'll see a different IP each time — the gateway rotates automatically when no session id is present. Sticky sessions: keep one IP across requests Some flows (login, multi-step checkouts, paginated results behind a cookie) break if your IP changes mid-session. Pin the IP by passing a stable session id: import uuid sess = uuid . uuid4 (). hex [: 8 ] # one id for the whole flow p = proxy ( country = " de " , session = sess , lifetime = 30 ) s = requests . Session () s . proxies . update ( p ) s . get ( " https://example.com/login " ) s . post ( " https://example.com/login " , data = {...}) # same exit IP When you

Australia was the first country to issue a ban in late 2025, aiming to reduce the pressures and risks that young users may face on social media, including cyberbullying, social media addiction, and exposure to predators.

The indictment, which was unsealed Friday, alleges the Volkswagen engineers used confidential insider information to buy stock in Rivian.

A normal secondary index can answer: status = "active" It cannot efficiently answer: documents containing "distributed database" LioranDB therefore has a dedicated text-segment architecture. Tokenization Text is split on non-alphanumeric characters. Depending on index options, tokens can be normalized to lowercase and filtered through stopwords. "Building Distributed Databases" becomes ["building", "distributed", "databases"] Segment contents A LioranDB text segment can contain several files and structures: Term dictionary Posting lists Document map Document-length norms Optional term positions Bloom filter Segment metadata A posting connects a term to the local documents containing it. "database" → [doc 2, doc 8, doc 19] Positions can record where the term appears inside each document. That enables more advanced query behaviour and phrase-aware features. Global and local document IDs Each segment assigns compact local IDs to its documents. A separate document map translates them back to global document IDs. This keeps postings smaller while preserving the external identity of the record. Bloom filters Each segment also maintains a Bloom filter for terms. Before reading a segment's postings, the query path can test whether the term might exist there. A negative answer is definitive. A positive answer means the segment may contain the term and should be checked. Query modes The text query layer supports modes such as: AND OR It also emits scored documents and metrics including: Query time Postings read Candidate documents Segments searched Full-text search is essentially a specialized database living beside the document database. Its data structures, compaction behaviour, scoring, and caching needs are different enough that treating it as a plain secondary index would be a mistake. Built by Swaraj Puppalwar under Lioran Group . Learn more: LioranDB Lioran Developer Solutions Lioran Group

Disk structures are durable, but updating them for every write is expensive. LioranDB uses memtables to absorb writes before flushing them to the on-disk B+ tree. What is a memtable? A memtable is an ordered in-memory map. In LioranDB, each entry contains either: Value ( bytes ) or: Tombstone A tombstone represents a deletion. The memtable also tracks: Approximate memory usage Minimum LSN Maximum LSN Entry count Put count Delete count The write path A simplified write path looks like this: Application write ↓ WAL durability ↓ Mutable memtable ↓ Immutable memtable queue ↓ Background flush ↓ Disk B+ tree The active mutable memtable accepts new writes. When it crosses a size limit, the engine rotates it into an immutable memtable. That immutable table is no longer modified and can safely be flushed in the background. Why ordered maps? LioranDB uses an ordered map for memtable entries. This helps because the flush process can emit keys in sorted order, which is friendly to the B+ tree and bulk-write paths. It also simplifies range merging between: Mutable data Immutable data On-disk pages Backpressure Background flushing cannot be allowed to fall behind forever. LioranDB therefore tracks limits such as: Maximum immutable memtables Maximum immutable bytes Partition-wide queue limits Maximum writer stall duration If the disk cannot drain the backlog quickly enough, the foreground write path slows down. That may sound undesirable, but controlled backpressure is much safer than consuming memory until the process dies. A memtable is not merely a cache. It is a pressure valve between CPU-speed writes and disk-speed persistence. Without that valve, the engine would either become slow on every commit or dangerously accumulate unbounded work. Built by Swaraj Puppalwar under Lioran Group . Links: LioranDB Lioran Developer Solutions Lioran Group

Most developers think of LioranDB as a document database. Internally, however, its storage engine does not understand documents, objects, fields, or JSON. It understands only: table + key bytes + value bytes That separation is intentional. The architecture LioranDB is split into two major layers: Application ↓ Document DBMS ↓ Transactional key-value engine ↓ WAL, memtables, B+ tree, pager and disk The engine exposes operations such as: get ( table , key ) put ( table , key , value ) delete ( table , key ) scan ( table , range ) The DBMS layer then adds document-oriented features: Collections JSON encoding Queries Updates Secondary indexes Text indexes Transactions For example, a secondary index can be represented as: idx:status:active → document_id A text index can be represented as: inv:database → posting_list The storage engine does not need to know what status , active , or database means. It only stores ordered bytes. Why this matters This architecture keeps the core engine small and reusable. The engine focuses on difficult low-level concerns: Durability Page management Transactions Recovery Ordering Concurrency Range scans The DBMS focuses on application-level semantics. This also makes it possible to build different data models over the same engine in the future. A document database is therefore not one giant component. It is a collection of carefully separated layers. That separation is one of the most important architectural decisions inside LioranDB. LioranDB is being developed by Swaraj Puppalwar under Lioran Group . Learn more: LioranDB Lioran Developer Solutions Lioran Group

On this episode of Uncanny Valley, we dive into accusations that China’s Moonshot AI stole from Anthropic, and how the US Army needs to cut back on AI use.

The offline messaging app surged in popularity in India amid protests in New Delhi.

The MCP (Model Context Protocol) ecosystem is growing fast. There are now hundreds of MCP servers available — but how do you know which ones are worth installing? After building and evaluating 60+ MCP servers ourselves, we developed a practical checklist that saved us from shipping broken tools. Here's the framework we use. The Problem Most MCP server listings tell you what the server does. Very few tell you how well it does it. You install something that sounds perfect, then discover: It activates on the wrong prompts (false positives) It pulls irrelevant context (retrieval drift) It sounds confident but gives wrong answers (ungrounded reasoning) It never improves from feedback Sound familiar? The 5-Dimension Evaluation Checklist Before installing any MCP server, ask these questions: 1. Trigger Precision Question: Does this server activate when (and only when) it should? Red flags: Overly broad trigger descriptions ("use for anything related to X") No documented activation conditions Activates on common words that appear in unrelated contexts Green flags: Specific, documented trigger scenarios Clear non-activation cases listed Tested against diverse prompts 2. Retrieval Quality Question: Does it pull the right context for the task? Red flags: Returns large chunks without filtering No citation or source tracking Retrieves plausible but outdated information Green flags: Targeted, minimal context retrieval Source attribution for every piece of context Version-aware (knows when data might be stale) 3. Reasoning Grounding Question: Are its conclusions tied to actual data? Red flags: Generates advice without referencing specific inputs Can't explain its reasoning chain Confident answers that contradict its own retrieved context Green flags: Every conclusion references specific evidence Explicitly flags uncertainty Gracefully handles missing information 4. Output Usefulness Question: Does the output actually solve your problem? Red flags: Generic responses that could appl

This is Part 18 of my series on the Microsoft Agent Framework. You can read the original post over on lukaswalter.dev . In the previous article , we looked at observability for agents. The main idea was to make a run visible as a chain of model calls, tool calls, approvals, and workflow events. Testing starts from the same idea. An agent run is not one answer string. It is a small application flow with several boundaries: user input -> prompt and context -> model request -> model response -> tool selection -> tool arguments -> tool execution -> structured result or final answer -> routing or workflow state If the only test is an end-to-end prompt against a live model, all of those boundaries are mixed together. When the test fails, you do not know whether the problem is the prompt, the model, the tool schema, the router, the workflow, or the real dependency behind the tool. The solution is not to pretend that an LLM is deterministic. The solution is to test each boundary at the level where it is deterministic, then add a smaller number of evaluation-style tests for behavior that genuinely depends on the model. This post covers: fake model clients tool contract tests structured output tests routing tests workflow tests eval-style regression checks The examples use xUnit-style assertions, but the testing approach does not depend on xUnit. The snippets focus on the relevant testing boundary and omit some application-specific factory and workflow setup. Do not start with the live model A live model test is useful. It is also expensive, slow, sometimes flaky, and difficult to diagnose. That makes it a poor replacement for normal unit and integration tests. I use a testing pyramid for agent applications: evals realistic model and user examples application integration tests agent + tools + storage + workflow boundaries deterministic component tests fake model client, tools, schemas, routing The bottom layer should be the largest. It should catch ordinary programming mistak

Microsoft does not create expert-tier certifications for experiments. An expert credential is a market declaration: this discipline is mature, hireable, and worth filtering résumés on. Multi-agent orchestration just got that stamp. The credential is Microsoft Certified: Multi-Agent AI Solutions Expert , earned by passing Exam AI-500 , now in beta with limited discounted seats per Microsoft's announcement . If you are weighing an exam AI-500 beta seat, this piece gives you what it tests, how it differs from AI-102 and AB-100, and a clear book-or-wait call. No menu of options. A decision. The short version of my position: the skills outline matters more than the badge. Microsoft just published its multi-agent product roadmap and formatted it as an exam blueprint. Read it either way. What AI-500 actually covers The announcement positions the certification for practitioners who can, in Microsoft's words, "operate at expert level in the agentic era." That phrase is doing real work. It is not about calling a model endpoint. It is about designing, orchestrating, and running systems where multiple agents cooperate, hand off work, and stay inside guardrails. Microsoft's own framing in the announcement names three capabilities: architecting complex, production-ready AI systems; orchestrating multiple agents and tools; and delivering scalable, governed AI solutions. My read of what those mean in practice, and why they are the right three: Orchestration of multiple agents and tools. Not one agent with a prompt. Several agents with routing, handoffs, and shared context. Governance. Identity, permissions, content safety, evaluation, and audit as exam material, not appendix material. Production-readiness. Deployment, observability, and lifecycle. The stuff that separates a demo from a system someone is paged for at 2 a.m. To be clear, that numbered list is my interpretation of the announcement's language, not a reprint of the skills-measured document. Pull the exact blueprint your

The carmaker has said it's owed a refund in the "tens of millions of dollars."

Users can now ask Attie questions about news, trends, and conversations on Bluesky and other apps on the AT Protocol.

Relativity Space announced plans to build a second rocket factory near Cape Canaveral, Florida.

Seller is a dedicated Marketplace app for people who list and sell items frequently.

# Module Resolution Algorithm (Part 1): How Node.js Finds the Right Module In the previous article, we explored one of the most fascinating parts of Node.js—the hidden Module Wrapper Function. We learned that every CommonJS module is wrapped inside a function before execution, and we also discovered that require() is not a JavaScript feature. It is provided by the Node.js runtime. But a very important mystery still remains. When we write: const fs = require ( " fs " ); or const math = require ( " ./math " ); how does Node.js know where these modules are located? How does it decide whether "fs" is a built-in module or a file inside your project? Why does require("./math") work even if you don't write .js ? And what happens internally before your code starts executing? The answer lies inside one of Node.js's most important systems: The Module Resolution Algorithm Understanding this algorithm is essential because every Node.js application uses it hundreds or even thousands of times while starting. What is Module Resolution? The word resolution simply means: Finding the actual file represented by the string passed to require() . Suppose you write: require ( " ./math " ); To you, "./math" looks like a file. But for Node.js, it is initially nothing more than a string. "./math" Node cannot execute a string. It needs the real file. So its first job is to answer one question: "Which exact file should I load?" The complete process of converting the string inside require() into an actual file on disk is called Module Resolution . Why Does Node Need a Resolution Algorithm? Imagine a project like this: project/ ├── app.js ├── math.js ├── database.js ├── auth.js └── utils/ ├── logger.js └── helper.js Now look at these statements. require ( " ./math " ); require ( " ./database " ); require ( " ./utils/logger " ); require ( " fs " ); require ( " express " ); All of them look similar. But internally they are completely different. Some point to your own files. Some point to Node's bu

Facebook is planning some big changes to try and keep its users from jumping to rival social platforms like TikTok - changes that sound dubiously similar to becoming a TikTok clone. Facebook head Tom Alison announced today that the platform will begin testing a "reimagined experience" later this year that will put a subset of […]