Name a design style, and AI event posters stop looking identical

At the top of the Hacker News front page, with about nineteen hundred points: a blog post showing that AI event posters stop looking identical once you ask for a design style by name.

The author starts with the village fayre posters everyone has seen: pastel airbrush, bunting, cartoon crowds. The complaint is not that they are bad. They are fine. They are all the same, and the repetition on its own is what grates.

So they tried. A careful brief, asking for clean, unfussy and bright, still came back as the same craft fayre template. What broke the loop was blunter: make another using a completely different design aesthetic of your choice. Out came flat Bauhaus geometry.

The second move is to ask the model what it just did. It named the style. Then, asked for a list, it offered fifteen to choose from. Risograph misregistration, Matisse cut paper, wayfinding signage, Memphis squiggles. Naming an aesthetic out loud is the whole technique.

Not everyone was convinced. Commenter tikhonj argues the better examples are still flat in attention. Every part sits at the same visual level and nothing pulls your eye, which is their complaint about generated code as well. Grant Sanderson wants mathematicians credited for more than their proofs.

A guest post on Terence Tao's blog. If machines generate proofs without understanding, proofs stop being a good proxy for what mathematicians contribute. His proposal: give academic credit to motivated explanations, where definitions arrive in the middle, once the problem they solve is clear.

Commenter jameshart carries that further. A machine proof of a famous conjecture would land the way a bigger Mersenne prime does. Another one existing is unsurprising, so the value is only in what proving it taught you. And one writer's rules for using an LLM without letting it write.

The method: write the piece yourself, then hand it over to find flaws, never to produce prose. Rule one: use no phrase it suggests. Rule two: forbid encouragement, since praise sends you back to your first draft. Then let it do the tedious catching.

Commenter semiquaver takes it further and writes every commit message and pull request description by hand again, letting an agent check the facts but never rephrase. Skimming agent-written diffs had been costing them their grasp of the code.

Stanford Medicine, in Nature Neuroscience. Lineage tracing in mouse embryos found two brain progenitor populations that emerge together and never overlap. One is committed to the forebrain and midbrain, the other to the hindbrain. The paper calls the brain a composite organ.

Commenter ksenzee points past the headline, and the paper backs it. Because the lineages are separate, the team grew human hindbrain motor neurons in a dish for the first time, the cells that ALS and SMA destroy.

A build of Brood War that models can only play through an agent, and none played past beginner level. Thinking costs real time. One Grok four point six run logged about eleven thousand reasoning tokens, issued six batches of commands in forty three minutes, and never built a fighting unit.

Commenter AntiRush remembers a Brood War bot tournament run at U C Santa Cruz in two thousand ten, in the early days of the game's scripting interface. Purpose built bots then, general models improvising now.