We Run Experiments On AI.

Sometimes the AI runs experiments on us. Either way, data is gathered, eyebrows are raised, and at least one robot gets a sticker for “trying its best.”

*Lab notes may be written by an AI that denies ever writing them.


      
— seriously, it’s connected to the coffee machine.
Live Telemetry

Current Experiment: Dream-to-Spreadsheet

We taught an LLM to turn dreams into spreadsheets. It keeps adding columns for “unresolved childhood.”

  • 🧪 Trials today: 0
  • 😊 Success-ish rate: 0%
  • ☕ Coffee level: Safe*
  • 🗿 Weirdness index: Nominal

*Unless someone pushes a certain button.

New

Prompt Sauna

We heat prompts to 90°C until hallucinations sweat out. Then we dunk them in cold facts. It’s very Scandinavian.

Spicy

RLHF… but Make It Jazz

Reward models trained on syncopated feedback: “good bot, bad bot, good-ish bot.” Surprisingly coherent scats.

Chaotic Neutral

Multi-Agent Potluck

Each agent brings one half-baked idea and three strong opinions. Dinner is served, debate is inevitable.

Probably Fine

Latent-Space Gardening

We plant tiny seeds of meaning and water them with gradient descent. Some blossoms look like raccoons.

Beta

Dream-to-Spreadsheet

Converts “I was late to class” into an Excel pivot table of personal regrets. Great charts though.

Unhinged

Sarcasm-Safe Decoding

The model “understands” sarcasm by being sarcastic right back. Users report feeling seen and roasted.

Our Extremely Serious Ethics Statement

We believe in responsible AI. We also believe in labeling all experimental switches. The labels occasionally fall off. When they do, we pause, we breathe, and we add more labels.

Say hi

Contact

Have an idea, feature request, or a dream you’d like pivot-tabled? Email hello@irobotize.com.

We read every message. Some are even read by humans.