标签：#p

Save it once, never lose it again Discussion | Link

Skills Are a Mess. Let's Fix That. Here's the problem: you write a skill for zeroclaw. It works locally. You push it. Someone else tries to install it. Nothing works. The error says "missing dependency" but doesn't say which one. Or it installs but the audit fails silently. Or the test harness just... doesn't run. Sound familiar? I've been watching the zeroclaw skills ecosystem grow. More people are authoring skills. More people are hitting the same walls. The v0.7.6 release is about tearing those walls down. What Actually Breaks Let's get specific. Three failure modes I see every week: 1. Install hell zeroclaw skills install my-skill # → Error: Failed to resolve dependency graph # → (no other output) You're left guessing. Is it a peer dependency conflict? A missing Python version? A circular reference in the skill manifest? The loader gives you nothing. 2. Audit blindness zeroclaw skills audit ./my-skill # → Audit complete. 0 issues found. # → (skill crashes immediately on first use) The audit passed. But it didn't check for the actual runtime errors — missing environment variables, incompatible tool signatures, malformed output schemas. It checked the manifest format. That's it. 3. Test harness that doesn't test zeroclaw skills test ./my-skill # → Running 3 test cases... # → All passed. # → (skill still hallucinates in production) The test harness runs your skill against mock data. But the mock data doesn't match real tool outputs. Your skill passes locally, fails in the wild. Why This Happens The current architecture treats skills as static packages. You define metadata in a skill.json , point to some functions, and assume it works. But skills are dynamic. They call tools. They depend on runtime state. They interact with the sandbox. The loader doesn't validate the runtime contract. The audit doesn't simulate execution. The test harness doesn't fuzz inputs. So you get false positives everywhere. "Works on my machine" becomes "works in my specific environment with

If you’ve ever worked with Arabic, Persian, Hebrew, Urdu, or any RTL (Right-to-Left) language on the web, you probably know the pain. Mixed RTL/LTR text rendering breaks unexpectedly. Punctuation looks wrong. Numbers don’t match the locale. Ellipsis appears on the wrong side. URLs inside Arabic text become unreadable. And emails or plain-text environments completely destroy formatting. After dealing with this problem repeatedly, I decided to build: rtl-text-tools A lightweight RTL text processing toolkit for JavaScript and TypeScript. It handles: RTL detection Direction normalization Arabic/Persian digit conversion RTL punctuation conversion Ellipsis fixing Unicode bidi wrapping CSS helpers DOM helpers And it works all the way back to IE11 with zero runtime dependencies. Why This Exists Most internationalization libraries focus on translations and formatting APIs. But very few actually solve the rendering problems of RTL text itself. For example: "مرحبا, رقم 123..." Visually, this often renders awkwardly in mixed-direction environments. You usually want: "...مرحبا، رقم ۱۲۳" That means: move ellipsis to the correct visual side convert punctuation convert digits preserve RTL readability That’s exactly what rtl-text-tools does. Installation npm install rtl-text-tools Quick Example import { fixRTL } from ' rtl-text-tools ' ; fixRTL ( ' مرحبا, رقم 123... ' ); // → "...مرحبا، رقم ۱۲۳" Arabic digits are also supported: fixRTL ( ' مرحبا, رقم 123... ' , { lang : ' arabic ' }); // → "...مرحبا، رقم ١٢٣" If the text isn’t RTL, it returns the original string unchanged: fixRTL ( ' Hello world ' ); // → "Hello world" Features 1. RTL Detection Detect whether text contains RTL scripts. import { hasRTL } from ' rtl-text-tools ' ; hasRTL ( ' مرحبا ' ); // true hasRTL ( ' שלום ' ); // true hasRTL ( ' Hello ' ); // false Supports: Arabic Hebrew Persian/Farsi Urdu Syriac Thaana N’Ko Samaritan Mandaic and more 2. Digit Conversion Convert Latin digits into locale-specific numerals. Persian

Most scraper demos lie by accident. They show the happy path: one URL, one clean page, one neat JSON object. Then the first real user tries a marketplace search page, a login wall, a JavaScript shell, a rate-limited product page, or a site that serves different HTML to every fetch path. The response still comes back as JSON, so everyone relaxes. That is the trap. A JSON response is not the same thing as a useful extraction. The failure mode agents hate AI agents do not just need scraped text. They need to know what happened. Bad extraction output looks like this: { "title" : "Example product" , "price" : "$29.99" , "availability" : "in stock" } That looks fine until you inspect the source and discover the page was a login prompt, a bot challenge, or a thin JavaScript shell. The extractor filled the schema because the schema was requested. Helpful. Like a smoke alarm that hums a little song while the kitchen burns. Better extraction output separates the data from the confidence and the failure class: { "status" : "failed" , "failure_type" : "login_required" , "confidence" : 0.94 , "extracted" : null , "evidence" : { "final_url_type" : "restricted_page" , "visible_content" : "login prompt" , "structured_data_found" : false }, "next_step" : "Use an authorised source, public item URL, feed, API, or sample HTML." } That is less flashy. It is also much more useful. The useful contract is not “scrape anything” “Scrape anything” is usually a warning label wearing lipstick. For agent workflows, the better contract is: Return structured data when the page provides enough evidence. Return a specific honest failure when it does not. Preserve enough metadata for the caller to decide what to do next. Never invent fields just because a prompt asked nicely. This matters for ecommerce, lead enrichment, price monitoring, competitor tracking, procurement, and internal research agents. If the agent cannot tell the difference between “product unavailable”, “page blocked”, “login require

Whisper is remarkably robust. But "robust" doesn't mean "immune to noise." If you've ever run a meeting recording through Whisper and gotten back garbage — or worse, confidently wrong text — the problem is usually the audio, not the model. Here's the thing: different noise types fail differently. Electrical hum causes Whisper to hallucinate syllables. Echo makes it drop words entirely. Static makes it confuse phonemes. Knowing which noise you have tells you exactly which fix to apply. This post covers: ✅ How each noise type (hum, hiss, echo, wind, static) degrades Whisper output ✅ A Python preprocessing pipeline that detects and removes noise before transcription ✅ How to call the StemSplit Denoise API for cloud GPU noise removal (no local setup) ✅ Measured WER improvements you can reproduce The Noise → Transcription Failure Map Noise Type What It Sounds Like How It Breaks Whisper Hum (50/60 Hz) Constant low-frequency "buzz" Inserts phantom syllables, lowers confidence Hiss High-frequency "shhh" Loses sibilants, confuses "s/sh/f" sounds Echo / Room reverb Words "bounce" and overlap Drops end-of-sentence words, merges phrases Wind Burst plosives, low-frequency rumble Transcribes as "[inaudible]", breaks sentence segmentation Static / crackling Random pops and snaps Breaks word boundaries, causes mid-word cuts These aren't hypothetical. They're reproducible failure modes. Let me show you how to handle each one. Prerequisites pip install openai-whisper requests python-dotenv soundfile numpy librosa You'll need: A StemSplit API key from stemsplit.io/developers (free 5-minute tier, no credit card) ffmpeg installed ( brew install ffmpeg / sudo apt install ffmpeg ) The Preprocessing Pipeline Here's the full pipeline before we break it down: Audio file → [Noise detection] → [Denoise via StemSplit API] → [Post-process: normalize, trim silence] → Whisper → Transcript Step 1: Detect What Kind of Noise You Have Before throwing everything at a denoiser, it helps to know what you

The RL Flywheel That Actually Works Here's what's breaking: You've got a reinforcement learning setup that trains, validates, deploys, and then... nothing. No feedback loop. No automatic retraining. No safety gates. Just a model that gets stale the moment it hits production. Sound familiar? I've been building RL systems for a decade. The pattern is always the same: great training pipeline, terrible deployment loop. You spend weeks getting 95% validation accuracy, push to prod, and three days later the distribution shifts. Your agent starts making garbage decisions. You scramble to retrain. Rinse. Repeat. This sucks. I know. The Real Problem The issue isn't training. It's the feedback loop . Most RL systems have: Training pipeline — works fine Validation — mostly works Deployment — fire and forget Observation — maybe some metrics Strategy update — manual, if ever Step 4 and 5 are broken. You're flying blind after deployment. The Flywheel Architecture Here's what a real RL flywheel looks like: Train → Simulate → Validate → Gate → Deploy → Observe → Analyze → Train Every arrow is automated. Every gate is a hard check. Every observation feeds back into training strategy. Let me show you the actual implementation. The Training Loop class RLFlywheel : def __init__ ( self ): self . model = Model () self . buffer = ReplayBuffer ( 1_000_000 ) self . safety_gate = SafetyGate () self . observer = OnlineObserver () def train_epoch ( self , episodes = 1000 ): for ep in range ( episodes ): states , actions , rewards = self . simulate_episode () self . buffer . store ( states , actions , rewards ) batch = self . buffer . sample ( 256 ) loss = self . model . update ( batch ) # Validate against known failure modes validation_score = self . safety_gate . validate ( self . model ) return loss , validation_score Notice the validation happens during training, not after. That's the first gate. The Safety Gate class SafetyGate : def __init__ ( self , thresholds ): self . thresholds = thre

The test passed. The runbook completed. Infrastructure came back online inside the RTO window. None of that means the organization can recover from an actual disaster. Disaster recovery testing is designed to succeed. Clean environments, pre-staged dependencies, known failure modes, available staff — each design decision is operationally reasonable. Collectively they remove the conditions that make real recovery hard. What the test validates is test completion, not recovery capability. The Test Is Designed to Pass Every design decision in a standard DR test tilts toward a successful outcome. The test window is pre-announced, so the right engineers are available. The scope is pre-defined, so unexpected systems don't surface mid-exercise. The environment is either isolated or pre-staged, so competing failures don't complicate the recovery sequence. The data state is known and clean, so integrity issues don't slow the restore. The declaration point is assumed, so nobody has to make an ambiguous call under pressure. A test designed to remove the variables that make recovery hard cannot produce evidence about what happens when those variables are present. What Disaster Recovery Testing Actually Excludes Declaration threshold. In a DR test, recovery starts at a pre-agreed time. In a real incident, recovery starts when someone decides the situation has crossed the threshold for declaration — a decision that is rarely clean and routinely delayed 45 minutes to several hours. That delay is inside the real outage window and outside the test clock. Dependency assumptions. DR tests run against known, pre-cleared dependencies. Real incidents surface undocumented dependencies that were never in scope — a configuration service that hasn't been touched in two years, an authentication endpoint that wasn't in the architecture diagram. Data state. Test environments use clean or pre-staged data. Real recovery requires handling whatever state the data was in at the moment of failure — pa

The company says it needs "significant" water resources to cool its data centers, and that access to abundant, affordable water is a challenge.

After using Claude Code, Codex, and Pi Agent for months, I wondered: how many AI agents are on my machine? I built a scanner. Here's what it found: Framework Active Archived Claude Code 192 191 Codex CLI 37 0 Pi Agent 8 sub-agents 12 scripts MCP Servers 8 - Total 448+ The Waste Duplicate calls : Same prompt → 3 agents (8-18% waste) Overqualified models : Simple tasks on expensive models (15-25% waste) Cache fragmentation : No shared prompt cache (12-20% waste) Zombie agents : Archived still indexed (2-8% waste) → 30-50% of AI API spend is wasted. The Fix AMA — Agent Management Agent bash pip install ama-core && ama scan && ama start Scans all agents across frameworks Smart routing (simple task → cheap model) Lifecycle management Local dashboard at localhost:8765 Free calculator: ama-agent-store.vercel.app/calculator MIT licensed. Feedback welcome!

Sony will deliver more than an hour of trailers and game news this week.

The Mall lets shoppers build a personalized feed of brands, track sales and drops, and discover products across thousands of retailers.

The AI giant behind Claude submitted paperwork on Monday that would take it public, just a couple of weeks after SpaceX’s splashy IPO announcement.

Lawsuit seeks $12,000 from startup that allegedly damaged home in robot tests.

BYD is giving its self-driving tech a big vote of confidence.

New article: “ Responsible Disclosure in the Age of AI: A Call for Urgent Action ,” by Melissa Hathaway. Abstract: Artificial intelligence is fundamentally reshaping the balance between vulnerability discovery and remediation. Frontier AI models are now capable of autonomously identifying exploitable software vulnerabilities at unprecedented speed and scale. This development exposes decades of accumulated technical debt created by a software industry that prioritized rapid deployment over secure-by-design engineering practices. Drawing on the evolution of software assurance, vulnerability disclosure frameworks, and U.S. cyber policy, this perspective argues that the current moment represents a strategic inflection point for governments, industry, and critical infrastructure operators. The author examines the growing tension between offensive and defensive equities in cyberspace, the emergence of AI-enabled vulnerability discovery capabilities in both the U.S. and China, and the increasing risks posed by unsupported legacy systems and AI-assisted code generation practices. Responsible disclosure can no longer remain a reactive or fragmented process, but must become a coordinated national and international resilience effort involving governments, software vendors, infrastructure operators, and emergency response organizations. The article concludes with an urgent call for accelerated remediation, large-scale patch management coordination, and sustained investment in automated vulnerability repair capabilities before adversaries exploit this rapidly narrowing window of opportunity...

Mike Schroepfer's Gigascale Capital has raised a large fund to back founders building climate-friendly solutions for the world's energy and material shortages.

After months of speculation about whether OpenAI or Anthropic would be first in their race to IPO, Anthropic on Monday reached a key milestone: filing to kick off the process with the U.S. Securities and Exchange Commission. The filing sets the stage for what's sure to be a massive IPO. As of its fundraise last […]

The company said Monday it has filed confidentially for an IPO.

Sony is sharing new details about some of its upcoming gaming-focused hardware, including pricing and August launch dates for its FlexStrike fight stick and its 27-inch monitor. The FlexStrike fight stick will be available starting August 6th - the same day as the new PlayStation-published fighting game Marvel Tōkon: Fighting Souls - and will cost […]

The new PlayStation monitor and fight stick arrive this summer, but you'll have to wait until later in the year to snag the Pulse Elevate wireless speakers.