Research #Coding agents#Google Nov 13, 2026 · Originally published Nov 12

Google pairs Gemini 4 Argon with the Z3 constraint solver to find Go bounds panics: all three planted bugs found plus three latent ones, two of which fuzzing missed

A practical take on lightweight formal methods: have the model turn the bounds checks the compiler leaves behind into solver constraints, then reproduce with go test.

Image: Google Developers Blog
Primary source Google Developers Blog · developers.googleblog.com Read the original ↗

// Key points

  • Go's SSA prove pass first removes bounds checks it can prove safe; only the surviving runtime.panicBounds traps, with the disassembly, go to Argon, which writes a Z3 script for each.
  • When Z3 returns sat it yields concrete input bytes that go test replays; any panic is a real bug regardless of whether the model's encoding was sound. An unsat result only means maybe correct.
  • It takes about a minute per function, dominated by Argon's translation, with Z3 itself finishing in milliseconds; it found three latent bugs in skill-lint.
  • Unseeded go test -fuzz missed two of the three planted crashes across repeated 60-second runs.

Builder's takeThe appeal is that every finding is real, so false positives cost almost nothing, which makes it a good CI complement to fuzzing. Our upload and parsing services in Go are exactly where these bounds bugs live; I would start with a few parser functions, aiming not for proofs but only for real, reproducible crashes.

// Background · from #Coding agents

Full timeline →
  1. Nov 13 Google releases Gemini 4 Hydrogen at $1.50 input and $7.50 output per million tokens, scoring 51 on the Artificial Analysis Intelligence Index, just above Argon's 50
  2. Nov 13 AWS publishes an enterprise rollout guide for Codex on Amazon Bedrock: sign in through IAM Identity Center and call GPT-5.6 Sol, Terra or Luna on Bedrock
  3. Nov 12 AWS releases AWS Emulator: SDK and CLI calls return locally in milliseconds with no AWS account needed, with source published under CC0

Every Monday, the week in AI in one email

Every Monday morning: the 6 AI stories that mattered most in the past seven days, with my take, in your inbox.

Your email is only used to send the weekly and is never shared. Every email has a one-click unsubscribe link. See the latest issue →