Vanja Petreski (Page 2)

Satirical cartoon: a haloed Sam Altman caricature holds a $1,000 SORRY! cheque while a CODEX vacuum sucks coins from a sleeping developer's laptop; robots stare at a locked door.

Fuck You OpenAI

And Fuck Sam Altman Too

A large analog gauge in a dark server hall, its needle swept past the blue arc into a glowing amber outer arc, with streams of light running to rows of server racks.

Overtime: When the Plan Runs Out, Credits Take Over

My harness stopped Claude Code and Codex at 95% of their plan windows, even when usage credits could have paid for more. Now it checks for usable credits first, keeps working until they run low, and says so in the status bar.

A steel rotary selector set into a concrete plinth, its pointer lit amber, beside a tower of stacked concrete slabs edged in blue light in a dark brutalist hall.

The Thinking Dial

What reasoning effort really changes in Claude Code, Codex and local models: thinking tokens, tool calls, cost, wait and usage limits. The evidence, the defaults that move under you, my own harness settings, and how to choose a level.

Two men talk on a sofa in a night-lit apartment; beside one man's gesturing hands a glowing node bursts into light paths, and light trails fan out from one point over the skyline.

The Switchboard: OpenRouter, Explained

One API key, about 350 models, dozens of hosts behind the popular ones. A complete guide to OpenRouter: how its routing, prices and privacy really work, how coding agents plug in, and where it would fit a three-agent harness.

A glowing violet cube rises from a processor at the center of a circuit-board city at night, while two cloud cities above it send thin beams of light down to the chip.

The Third Mind: Local AI for When the Cloud Runs Out

OpenCode on open-weight models, running on a MacBook Pro beside Claude Code and Codex: the agent that works when both are out of quota. Memory, prompt caching, uncensored models, self-updating lineups and a coding duel with Claude.

Beams of light from a drafting table, a terminal, a data chart and a wall of product cards meet above a night workbench where small robots assemble a glowing architectural model.

We Are Product Builders Now

Agents now ship while I sleep. The scarce work moved from writing code to understanding it, and I think engineering, product, design and data will fold into one role. A short documentary and the case for the product builder.

A cyberpunk archive corridor of glowing glass slabs etched with lines of text, receding to a bright core of light; a searchlight from the ceiling lights a few lines in amber.

Total Recall: How QMD Works

An 8-minute documentary and a field guide to QMD, the local search engine that gives coding agents a memory: one real query traced stage by stage, the harness that makes agents use it, and the numbers from six months of daily use.

Four glowing geometric medallions on rising pedestals beside a tall gate of light, with an open archway into a bright library where abstract figures of light walk in

How to Get Claude Certified: Four Exams, and Who Can Sit Them

Anthropic's four certification exams cost $99 to $175, are proctored by Pearson VUE and are open only to people at Claude Partner Network firms. Who can sit what, how the exam works, how to prepare, and the free Academy courses for everyone else.

Abstract AI assistant orb sending threads of light through a frosted veil to a glowing article page, above an analytics dashboard with an empty source list and a rising bar chart

Claude Cites My Blog. My Analytics Call It Direct.

One old post brought in 24 of my 30 new subscribers in two weeks, every one labeled Direct, while Google sent almost nothing. Claude cites it, through links that drop the referrer. The evidence, a check you can run, and what it can't prove.

Golden crystal banana spraying a mosaic of small image tiles, a precision optical instrument projecting one large landscape, and a balance scale between them

Nano Banana 2.1 vs Sunburst at Max: Cheaper, Still Behind

Google lists Nano Banana 2.1's 1K image output at $0.0336, about a sixth of what one Sunburst image at max cost me. Sunburst still leads all six independent leaderboard views I checked. Prices, Google's 4K discrepancy, features, and which jobs suit which model.

A rain-soaked cyberpunk city at night: a central tower of glowing terminal panes linked by neon wires, with three glass towers branching from its base on lit skybridges.

One Task, One Session: The Parallel Agent Field Manual

A 9-minute documentary and a field manual for running Claude Code and Codex in parallel: when to stay, clear, branch, fork or spin off, when you need a worktree, what it costs, and how to make the agents do it for you.

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.

Three glowing machine cores on a rain-soaked workbench at night, the centre one being hoisted into place, lit in violet and blue

Grok 4.7: Same Price, Longer Runs, One 402

xAI shipped Grok 4.7 today: a larger base model, 500k context, xhigh still the ceiling, same $2/$6 price, and a few contradictions in its own pages. What the model card measures, and how every Grok pin on my desk moved to 4.7 the same afternoon, balance wall included.

Latest