Vanja Petreski

A violet crystal and a three-band plan panel send blue light paths through three columns of glowing cyan cubes in a dark server hall into one white cube.

Dynamic Workflows Move to the Server

An agent can now write a program that runs many agents in phases on Anthropic's servers. How a run works, what it costs, and what to check first.

Chat cards over a night-city desk: calm blue ones above, cracked red ones sealed off by a violet glass door, beside a policy page with one highlighted line.

The Cruelty Clause: What Anthropic Actually Banned

One bullet, two qualifiers and a carve-out paragraph: what Anthropic's new rule on cruelty toward its models says, and what it means for you.

Two drained translucent usage gauges refilling with light beside a small glowing gift box holding a circular refresh arrow, on a night-city desk.

You'll Thank Me Later: Free Limit Resets

Hit your weekly limit on Claude or Codex? Check the usage page first. A free reset may be waiting, and here is how to use it well.

A small stack of glowing credit chips beside a larger translucent toolkit crate, an hourglass and two glowing doorways to cloud cities on a night platform.

Claude for Startups: The $1,000 Is the Small Part

What the $1,000, the free Team year and the fine print are actually worth, and how AWS Activate credits can pay for Claude on Bedrock.

Two glowing AI cores, one amber and one cyan, caged in metal rings and cabled to a central monolith of light in a dark, cathedral-like server hall.

The Harness: Two AIs, Zero Trust

A nine-minute documentary about everything around the models: one rulebook for Claude and Codex, shared memory, cross-provider review, account guards, clean handovers and loops that know how to stop.

Two glowing AI server towers linked by a light bridge, an empty third pedestal with an unplugged cable, and two keys tethered to separate doors.

I Fired My Busiest AI Reviewer

Same $700, one provider fewer. What 620 review receipts say about the cut, what it costs, and how two Claude accounts now route by directory.

A small robot with a glowing clapperboard beside a projector made of terminal windows, projecting an AI video pipeline onto a giant screen in a neon city.

The Explainer Video Is the New TL;DR

An agent researched, wrote, voiced, animated and checked a 4:25 explainer on how coding agents work. Here is the complete pipeline behind it, what it cost, and what it still cannot check.

Three illuminated optical engines on a dark workbench against a night city skyline, with violet and cyan engines connected through a glass prism and an amber engine standing apart.

ChatGPT Pro 500: Same Budget, Fewer Providers

Pro 500 offers 25× the Plus allowance. Optional Ultrafast consumes included usage at 8× and purchased credits at 6× Standard. Is the $700 Claude–Codex pair a better use of the trio’s budget?

A night-time classroom with empty desks and tablets, a glowing hourglass at the center, floating progress dashboards, a small robot and an open door to an outdoor workshop

Alpha School: Two Hours of AI a Day, and What It Costs

A private school network that says children learn twice as fast with two hours of AI a day. What it is, who pays for it, what it costs, what the evidence shows, and whether children outside the U.S. can attend.

A steel vault door stands ajar in a dark data center; blue light spills through the gap, where streaks of light race along a curving track between rows of glowing server racks

ChatGPT Pro Max: The $500 Price Leaked, the Limits Didn't

OpenAI hasn't announced it, but a $500-a-month Pro Max plan has been spotted in ChatGPT's subscription screen, pitched as "Fastest Work and Codex". What the card shows, what OpenAI's own rate card already says about speed and allowances, and what to check at DevDay.

Three glowing machine cores on a wet steel floor at night: a blue star, an amber sun and a silver crescent moon, with a balance scale standing between the star and the sun

GPT-6 Sol and Luna: Cheaper Than Astra, Not Better

A fifth of Astra's price for Sol, a hundredth for Luna. My rule for the Codex seat, written before the charts: switch only to a model that beats Astra at maximum settings and costs less. Sol costs less. On every chart OpenAI published, it doesn't beat Astra.

Three glowing machine cores on a steel rack in a night workshop; the violet one is mid-swap, a heavy core lifted out on chains above a smaller, brighter core seated in its socket

Opus 5.5: Fable's Level at 40% of the Price

Anthropic shipped Opus 5.5 on September 22: by its own numbers, Fable 5.1's level on most work, at $4/$20 per million tokens against Fable's $10/$50, with medium as the new default effort. What the release measures, where the catch is, and how my Claude seat left Fable the same afternoon.