Replacing LLM calls with deterministic code cuts compliance alert costs from $290K to under $26K
josephdviviano · x · 2026-10-12
Garry Tan endorses the approach: replacing LLM calls with deterministic code is a no-brainer and yields better code that matches what users want.
Real-world case from @aj: they built a harness using @typesafeai's Jev that learns the job as it runs, gradually moving steps from LLM calls to code. Running 100,000 compliance alerts cost over $290K on Opus 5; with agentrun() they got it down to under $26K — roughly a 90% cost reduction.
More from coding & agent
- David Fowler: build CLIs for agents to explore systems and fix bugs autonomously — mariorod1 · 2026-10-12
- rtoml v0.14 Adds Python 3.15 Support, i128 Ints, and Big Speedups — samuelcolvin · 2026-10-12
- Reverse-engineering ChatGPT's Intelligent UI: DIL language, server-side compilation and sandboxed runtime — rohanpaul_ai · 2026-10-12
- Reverse engineering leaks three unannounced Grok Bot features, versioned memory leading — bfrench · 2026-10-12
- badlogic demos durable codemode: persisting agent state so long tasks survive aborts — max_paperclips · 2026-10-12
- supermemory packages agent context into one API with memory, retrieval built in — julianweisser · 2026-10-12