Probably: a toy programming language where LLMs power if statements
Vjeux · x · 2026-09-19
Developer southpolesteve unveiled Probably, a toy programming language that bakes "Jev" (LLM-based fuzzy judgment) into the language itself:
- feels asks an LLM a question, match routes between natural-language descriptions, and while loops until something "stops feeling true"
- The division of labor: Jev makes the decisions, an LLM does the writing, and a small program ties it together
- The author admits it's a toy, but it shows what a language-level "AI if statement" could unlock
Meta engineer Vjeux and others boosted it with an "I love and hate this" reaction.
Related event: Probably: an experimental language that bakes LLM judgment into syntax(3 posts)→
More from coding & agent
- Pydantic Creator Benchmarks Jev vs Sonnet: 2.6x Cheaper, 3.7x Faster in 17 Lines — samuelcolvin · 2026-09-19
- GPT-6 Astra clears Geometry Dash demon level Jumper with all 3 coins — imjustnewatai · 2026-09-19
- Greg Kamradt: Humans with AI still beat AI with AI on productivity — GregKamradt · 2026-09-19
- Veteran ML engineer: Jev may push agent tool-calling back to discriminative models — multiply_matrix · 2026-09-19
- Box CEO demos Jev for instant enterprise document triage at near-zero cost — multiply_matrix · 2026-09-19
- Walrus Memory Launches Portable Memory for AI Agents Across Apps and Models — udmrzn · 2026-09-19