Session

Never Trust a Monkey: From AI Slop to Code You Can Ship

AI writes 42% of committed code, and 96% of developers don't trust it. We gave infinite monkeys GPUs — sometimes they produce Shakespeare, sometimes `assertEquals(true, true)`.

The Intent-to-Code Chasm is the central challenge of 2026. Every previous abstraction from compilers to VMs to cloud was deterministic; AI is stochastic, and our safeguards (reviews, tests, professionalism) still assume a human wrote the code. At 25,000 lines overnight, those assumptions collapse.

Three-part framework: Chasm (why the intent gap is structurally new), Context (how structured knowledge bridges it), Chain (a verifiable flow from intent → spec → locked tests → code, where no monkey validates its own work). Includes a real eval journey from 15% to 99% where better context beat a better model.

5 deliveries including JFokus 2026 (top 2 highest-rated talk) and Voxxed Days Amsterdam 2026 keynote. Scales from 15-min keynote to 45-min deep dive — the compressed keynote version was the highest-rated keynote at Voxxed Amsterdam. Strong keynote candidate. Solo talk.

Baruch Sadogursky

Member of DevRel Staff, Tessl AI

Nashville, Tennessee, United States

Actions

Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.

Jump to top