Nerd Snipe with Theo and Ben

Quote · Nerd Snipe with Theo and Ben

We Tested GPT 5.6 Sol Early

Explore episode Jul 9, 2026

Where this was said

Burning Tokens, Long Runs & Practical Lessons

At 1:04:45 · chapter starts 1:00:20

The hosts pull back from the extreme numbers and reflect on what actually moved the needle. The $65k Executor port was a meme — Ben admits it up front. But the days spent at $1,000 worth of tokens (about 1 billion) produced real, shipped work: Ben built a full Hermes agent interface system including a mobile app, web app, Mac Mini server, and Cloudflare tunnel architecture, all from a single coherent run. The key insight from both hosts is that the right mental model isn't 'do harder tasks' — it's 'go further in both directions.' Start earlier in the process, before you've even thought the problem through, and end later, after the agent has opened the app, tested its own work, responded to PR comments, and self-merged. These extended delegation loops are where the real leverage is found.

Technology
1B tokens for full Hermes app stack

We Tested GPT 5.6 Sol Early · Jul 9, 2026

Ben spent approximately 1 billion tokens (around $1,000 at API pricing) to have 5.6 build a full Hermes agent interface including mobile app, web app, Mac Mini server, and Cloudflare tunnel.

Technology
Giving the Model Your Psychosis

We Tested GPT 5.6 Sol Early · Jul 9, 2026 Technology

Ben spent an entire night in deep back-and-forth dialogue with Claude Code to build an agents.md that embedded a specific, unusual worldview into his project context. The result: UI outputs with genuine personality that escaped generic LLM patterns. Out-of-distribution prompting produces out-of-distribution results.

Similar quotes