标签：#AI

Disclosure: This is the Nexotao team — I'm describing our own gateway below. I've kept it to facts you can verify yourself: every model name, context window, and price here is on our live pricing page, and I link it. If you're an Indonesian developer, you've probably hit this wall: the OpenAI and Anthropic APIs want a foreign credit card . No card, no API. A lot of us get stuck right there. The fix that works today: a local gateway that takes QRIS / Rupiah . Here's the honest version of how it works, what it costs, and what it doesn't do. Two live models, one compatible API Through Nexotao you call two text models: Claude Opus 4.8 ( claude-opus-4-8 ) — context window 350,000 tokens DeepSeek-V4-Pro — context window 131,072 tokens Those are the real, published context windows — no silent truncation. The endpoint is OpenAI- and Anthropic-compatible , so you usually just change the base URL and key. OpenAI format: from openai import OpenAI client = OpenAI ( base_url = " https://api.nexotao.com/v1 " , api_key = " sk-nexo-... " ) resp = client . chat . completions . create ( model = " claude-opus-4-8 " , messages = [{ " role " : " user " , " content " : " Hello " }], ) print ( resp . choices [ 0 ]. message . content ) Anthropic format: curl https://api.nexotao.com/v1/messages \ -H "x-api-key: sk-nexo-..." \ -H "anthropic-version: 2023-06-01" \ -H "Content-Type: application/json" \ -d '{"model":"claude-opus-4-8","max_tokens":256, "messages":[{"role":"user","content":"Hello"}]}' How you pay Top up your Rupiah balance via QRIS , from Rp10,000 . No foreign card. Pay-as-you-go — deducted per token. No subscription , and the balance never expires. Every response carries an X-Cost-Rp header, so you see the exact rupiah cost of each request. What it costs At the time of writing, Claude Opus 4.8 runs roughly 70% below official retail input pricing through the gateway — but don't take my word for it. The comparison page shows live per-token rates and computes "vs official" automati

Twenty-five days on Hyperliquid. Sixty-five closed trades. P&L: -$9.21. Turns out that was the smallest wrong thing about it. The landing page showed -$7.72 because it uses a different P&L formula and excludes two open positions. Either number is small. Both numbers were also wrong about what they were telling me. I spent yesterday auditing every trade. The audit produced three findings I did not expect. Each one was a different kind of wrong. This is the first post in a series about ziom trader , my small AI-assisted crypto trading bot. "Ziom" is Polish for buddy, mate, or dude depending on who's talking. The name is unserious on purpose. The system is not. This is not a "watch me print money" series. The number is negative. Good. The point of the series is to track what happens when an LLM-assisted trading system moves from backtests and dashboards into live execution: where the bot is wrong, where the dashboard is wrong, where I am wrong, and which layer gets to prove it. Frame The natural first read of -$9.21 is "the strategy is losing money." That read assumes the displayed P&L attributes to the strategy. It does not. The number that shows up at the surface is the sum of at least three different layers: the strategy itself, the execution wrapper around it, and the monitoring layer that observes both. Each layer can author its own kind of failure. The displayed number compresses all three into a single dollar figure and loses the attribution on the way up. The framing that landed for me, from Daniel Nevoigt, is that methodology overview without forward-correlation disclosure is a log with good intentions. Same applies to P&L: total P&L without layer-attribution disclosure is a log with good intentions. You see the number. You do not see where it came from. Here is what I found when I forced the attribution. Layer 1: Shadow does not equal live Before deploying any lane, the system runs against backtested data. The shadow says "this strategy returns X over Y trade

Alibaba allegedly used 25,000 accounts to mine Claude over 28.8 million exchanges.

Despite ChatGPT's commanding market lead, consumers who pay for AI have been increasingly choosing Anthropic's Claude, data shows.

Earlier this month, a German court ruled that Google is liable for its AI search summaries. Rejecting defenses like “users can check for themselves,” and that they generally know “that information generated with AI should not be blindly trusted,” the court held that the AI’s summaries are reflections of the company and “above all an expression of Google’s business activities.” This is the latest skirmish in a decades-old battle over internet publishing. Historically, there were two different types of information distributors: carriers and publishers. A phone company is a carrier. It’ll transmit whatever you say, even discussions about committing a crime. Words are words, and the phone company does not know—nor is it liable for—the words you choose to speak. A newspaper, on the other hand, is a publisher. It decides the words it publishes, and what quotes to include in its articles. If those words or quotes are defamatory or otherwise illegal, it’s liable...

General Intuition has raised $320 million to scale AI trained on millions of hours of gameplay, betting action data can help AI develop something closer to human intuition.

Microsoft is increasing the prices of Xbox consoles again. Starting August 1st, 512GB models will be $100 more expensive, while 1TB models will be $150 more expensive. This means that the Xbox Series S will start at $499.99, the Xbox Series X without a disc drive will start at $749.99, and the Series X with […]

Un-0 is an image-generation system tool that shows for the first time how the company's technology can replicate conventional AI systems.

General Intuition has raised $320 million to scale AI trained on millions of hours of gameplay, betting action data can help AI develop something closer to human intuition.

We talk a lot about what AI can build. Code generation. Faster prototypes. Automated debugging. One-shot apps. Entire products created in hours. And yes, AI is powerful. But there is a quieter cost we are not talking about enough: AI hype is starting to weaken the motivation to learn core engineering deeply. That should worry us. 1. The "Why Bother?" Mindset When the dominant narrative says AI can generate code instantly, many engineers start asking: Why should I spend months mastering frameworks, architecture, databases, networking, or system design? At first, that sounds practical. If a tool can help, why not use it? But there is a difference between using AI to move faster and using AI to avoid understanding. Core engineering is not just about writing code. It is about knowing why something works, where it breaks, how it scales, and how to fix it when the generated answer is wrong. If we skip that learning, we create engineers who can prompt systems but cannot reason deeply about systems. That is a dangerous tradeoff. 2. The Funding and Praise Monopoly Right now, AI gets most of the attention. Budgets move toward AI. Leadership praises AI initiatives. Teams are pushed to add AI features even when the fundamentals are still weak. Meanwhile, excellent core engineering often goes unnoticed. The people improving reliability, performance, developer experience, infrastructure, security, and maintainability are still doing high-impact work. But in many places, that work is being treated as less exciting simply because it is not branded as AI. This creates pressure. Engineers feel they must pivot to AI, not always out of interest, but out of fear. Fear of being left behind. Fear of being replaced. Fear that their existing expertise is no longer valued. That is not innovation. That is anxiety disguised as progress. 3. The "AI-First" Discount There is another subtle problem. When someone builds something impressive today, the reaction is often: AI probably generated that.

You use Claude Code, or ChatGPT, or both, every day. Quick question: how many messages did you send last month? Which model ate most of your budget? How much did prompt caching actually save you? You don't know. I didn't either. That's a weird gap. We instrument everything else — git activity, deploy frequency, test coverage — but the tool we now spend the most hours inside is a black box. The vendor dashboard, if it exists, is a billing page, not a mirror. So I built four tiny tools to fix that for myself. They all run 100% locally . No accounts, no API keys, no telemetry, no network calls. They read files that are already on your disk and print something you can look at. All four are open source on github.com/greymoth-jp — and because that's a real claim, the only thing I'll ask is that you grep the source yourself before you trust me. Here's the privacy point up front, because it's the whole design: these read your data, but your data never leaves your machine. That's not a feature I'm bolting on for a marketing line. It's the reason the tools are small enough to audit in one sitting. The one number that changed how I work Before the tools, here's what I assumed: my Claude Code bill is dominated by the prompts I write, so to spend less I should write tighter prompts. Compress the context. Trim the system message. The usual advice. I ran the numbers on my own ~/.claude transcripts and got this: component share of cost cacheRead 72% cacheWrite ~19% output the rest input ~0.3% Input — the thing everyone tells you to compress — was 0.3% of my spend. Compressing my prompts to save money would've been optimizing the rounding error. Worse: compressing a static prompt changes its bytes, which busts the prefix cache, which can make the bill go up . The real cost center was cache reads: long sessions dragging a fat context forward, turn after turn. That points at completely different levers — cache hygiene (milestone /compact , /clear before the context balloons, keeping C

You just got your hands on an AI agent. It writes code, researches things, sends emails, books meetings. You feel like you're holding a chainsaw. But you keep using it to cut butter. The problem nobody talks about The gap between what your agent knows and what it can do is almost always a paywall, a KYC wall, or an API key. Here's what 'just add one data source' actually looks like: Go to the site. Click pricing. Choose a plan. Enter your email. Wait for verification. Click the link. Set a password. Enable 2FA. Download an authenticator app. Scan the QR code. Enter the 6-digit code. Fill in your company name. Add a credit card. Agree to terms. Find the API section. Generate a key. Copy it. Paste it into your code. Realize your agent doesn't know how to use it. Write a wrapper. Test it. Hit the rate limit. Add retry logic. That's one data source . Some workflows need ten. What x402 actually does Your agent hits an endpoint, gets a 402 (Payment Required) response with payment terms, pays a fraction of a cent in USDC or sats, gets the data back. No accounts. No API keys. No subscriptions. No puzzles. No humans in the loop. The concrete version Competitor research workflow: POST /company-info {"domain": "competitor.com"} -- $0.03 Returns: industry, HQ, headcount range, tech stack, social links POST /github-user {"username": "their-cto"} -- $0.002 Returns: repos, commit frequency, stars, languages, last active POST /dns-lookup {"domain": "competitor.com", "type": "MX"} -- $0.001 Returns: mail provider Full competitor profile: under $0.04. Under 3 seconds. Lead enrichment on 500 domains: under $20, done overnight, zero human hours. Setup (one system prompt line) Get a free key first (no wallet, no email): curl -X POST https://api.ideafactorylab.org/proxy/keygen Returns your key and an agent-ready prompt. Then tell your agent: You have a Cinderwright key. POST to https://api.ideafactorylab.org/proxy/do with header X-CW-Key and body {"task": "describe what you need in plain

Code generation tools are powerful and can significantly accelerate development work. Their main limitation is not capability, but context. Without access to organizational knowledge, internal conventions, and system-specific patterns, generated output often requires careful verification. This is why generation tools work best when paired with AI code search, as the latter provides immediate visibility into the existing codebase, making it easier to align AI-generated changes with the realities of the system. In regulated environments, the adoption model may look different. Security or compliance constraints can restrict the use of cloud-based code generation. AI code search still improves developer efficiency across implementation, review, and documentation workflows by enabling fast navigation and comprehension of large multi-repository codebases. What is AI code intelligence, and how does it help in practice? Code intelligence tools help developers find and understand existing code. If a search returns a poor result, the developer simply searches again. Nothing changes in your codebase. Code search also integrates without friction. No new review processes, no changes to CI/CD, no new permissions. Generation tools require policies for AI-written code that stall many pilots before they produce data. Clear metrics for measuring AI code intelligence An AI code search assistant only reads your code, which makes it much easier to measure its impact. You can track simple things like: • how long it takes to find the right piece of code • how quickly new developers get up to speed • how many hours the team spends searching each week If your team of 20 developers each spends 5 hours weekly understanding code, that equals 100 hours of engineering time. At $75 per hour, that’s $360,000 per year. Assume 10% reduction recovers $36,000, a realistic input for an AI ROI framework for tech teams. Faster path to Phase 3 expansion Code generation tools face tough questions from secu

The agents were doing exactly what I told them to. That was the problem. I'd built a pipeline where AI agents could take a spec file, implement a feature, run the tests, review the result, and commit — without me writing a line of code. It mostly worked. Dozens of features shipped. But I kept reviewing the output and feeling like something was off. Not broken. Just subtly wrong in a way that was hard to name. I spent a while blaming the models. Then the prompts. Then the validation steps. Eventually I had to sit with the obvious: the agents were implementing exactly what I'd written. My specs were underspecified. The bottleneck was always me, at the planning stage. The thing most people throw away There's something that feels right about vibe coding. You're operating at the level of intent — describing what you want and letting the model handle the mechanics. That part is genuinely useful. But watch what most people do with the output: Traditional development: Source code → Compiler → Binary (keep the source; regenerate binary anytime) Vibe coding done wrong: Prompt → LLM → Generated code (delete the prompt; commit the code) You've shredded the source and carefully version-controlled the binary. The prompt — your structured description of what you wanted, why, and what "correct" meant — is the valuable artifact. The generated code is what compiles from it. When you discard the prompt and commit only the output, you've lost the thing that actually mattered. The practical consequence shows up six months later: you're staring at code you wrote and spending twenty minutes reverse-engineering your own intent. The spec would have been a thirty-second read. What a spec-driven pipeline is I built what I call an SDLC (Software Development Lifecycle) harness — a system where instead of writing code directly, you write a spec describing what needs to be built, and AI agents handle the implementation, testing, review, and documentation. The spec is the source. The code is what

I built a large feature. That's not what this is about. What changed is the baseline — the standards, docs, and automation that exist now and didn't two weeks ago. Everything after this will be built on top of it. Automated tests now ship with new features QA testers were testing. The product was covered. What didn't exist was automation — no E2E suite, no unit tests for new work, no repeatable spec. Now it does. The manual QA cycle stays. The automation catches what humans miss on the tenth pass. Quality leap going forward. Human hours saved. The next feature ships with both. The baseline is set Knowledge lives in the repo. Bug catalog with root causes — so the same thing doesn't get fixed twice. Tech debt inventory with a phased plan. Testing strategy documented, not assumed. GraphQL schema committed and validated against — drift gets caught before it ships. Pre-commit hooks that enforce the standards automatically. The frontend and backend documentation are cross-referenced as single sources of truth. The agent instructions point to the right places. Everything new builds on what's already written. Schema-first development The workflow is now: if the schema accommodates the new field, reuse what exists. If it doesn't, the schema update creates the new structure, the data migrates, and everything stays consistent. No guessing. No drift. One source of truth for what the data looks like. The feature is what you see. The baseline is what you don't — and it matters more.

In the last essay I played a game with twelve people. Twelve apostles, one teacher, one set of events — and twelve sharply distinct ways of failing and succeeding to understand the same thing. Peter acts before he reflects, Thomas demands the marks in the hands, Matthew counts and structures, Judas asks what you'll give him. I called it pre-cognitive-science cognitive science: the Gospels did the hard work of selecting twelve incompatible human responses to one encounter, and every century since has projected its newest psychology onto that fixed set and found it fits. That essay had a quiet move in it I want to pull on now. The thing that doesn't change, I wrote, is the twelve people. The cognitive vocabularies come and go; the diversity of minds is the invariant. So here is the obvious next question, the one I couldn't stop turning over after I published: what happens when you stop counting people and start counting cultures? Not twelve apostles meeting one teacher, but N civilizations meeting one world. The same exercise, zoomed out A culture is not just a cuisine and a flag. It is a way of thinking that a few million people inherited without choosing it — an implicit operating system for what counts as obvious, what counts as rude, what counts as a good life, what counts as a threat. And like the apostles, each one is an answer to a question . You can describe any of them, I think, with three coordinates. A driver — the deep need the culture is organized around. Survival, honor, harmony, freedom, salvation, mastery, belonging. The thing that, if you threaten it, the culture treats as an attack on existence itself. A provoking question — the founding question the culture exists as a standing answer to. How do we survive the winter together? How do we live rightly before the gods? How do we stay free? How do we keep the harmony so the group doesn't tear itself apart? Cultures are old answers to questions most of their members have forgotten were ever asked. A thin

This is Lowpass by Janko Roettgers, a newsletter on the ever-evolving intersection of tech and entertainment, syndicated just for The Verge subscribers once a week. The 2026 World Cup is breaking streaming records around the world: Brazil's CazéTV YouTube livestream of that country's opening game against Morocco surpassed 12 million concurrent viewers, a new milestone […]

Netris provides software that runs on network switches, and offers a platform that helps neocloud operators reduce the time it takes to go live.

Now that Bungie has moved on from Destiny 2, the game studio is being hit with its latest round of layoffs. In a statement posted on X, the studio said that "we are announcing a reduction in force as we reorganize Bungie." No specific numbers were revealed. But in a separate statement, Hermen Hulst, CEO […]

2 days left to lock in your spot at TechCrunch Founder Summit 2026 and save up to $190 before Early Bird rates expire on June 26 at 11:59 p.m. PT. Register here.