Users praise the GPT-5.5 executor with GPT-5.6 advisor setup because it proves most tasks do not need frontier models and shows the value of combining cheaper models for cost savings.
Based on 3 visible X reactions from 5 accounts; directional sample.
Ask a question below.
Published answers will appear here.
I wish more AI devs would pay attention to the benefits of combining models. I am very curious how models from different providers (including open-weight ones) would perform as well. So much ground to explore and experiment with. https://x.com/omarsar0/status/2074857582536130882?s=20
This is proof that most turns never needed the frontier model in the first place. The real asset here is the escalation trigger. Tune it too tight and you pay full price anyway. Tune it too loose and quality leaks quietly, one unescalated turn at a time. Cool that you created this yourself. 👊🏽
@omarsar0 Variety in application is meaningful too. I recently stumbled onto an interesting path. I ask ChatGPT a lot of questions about music and that lead to discussions about my intellectual approach. Applying that knowledge to my AI’s interactions with me has been transformative.
Here’s a great post on driving down costs, while maintaining high performance, with frontier intelligence as a manager and lower cost models for the workhorse tasks. This will be the template for what model routing looks like in the future. “We started this experiment expecting to measure how much Fable’s 2x premium would increase cost. We were surprised to find that Fable’s effective delegation actually decreased cost overall. It specified constraints and outcomes instead of spelling out the implementation, gave feedback instead of making fixes itself, and in most cases never touched the code at all. These are the habits of a good manager.” The industry is increasingly figuring out what it looks like to mix models together to be able to get targeted performance levels and optimal cost structures. Of course, the only way to get this is to have a deep understanding of the business problem you’re trying to solve and how to effectively route work to different models. If you’re in the applied layer - whether it’s customer support, legal, finance, or coding - this is how your harness will become a core area of differentiation.
Custom harnesses call premium models only for complex routing decisions.
I wish more AI devs would pay attention to the benefits of combining models. I am very curious how models from different providers (including open-weight ones) would perform as well. So much ground to explore and experiment with. https://x.com/omarsar0/status/2074857582536130882?s=20
This is proof that most turns never needed the frontier model in the first place. The real asset here is the escalation trigger. Tune it too tight and you pay full price anyway. Tune it too loose and quality leaks quietly, one unescalated turn at a time. Cool that you created this yourself. 👊🏽
@omarsar0 Variety in application is meaningful too. I recently stumbled onto an interesting path. I ask ChatGPT a lot of questions about music and that lead to discussions about my intellectual approach. Applying that knowledge to my AI’s interactions with me has been transformative.
Here’s a great post on driving down costs, while maintaining high performance, with frontier intelligence as a manager and lower cost models for the workhorse tasks. This will be the template for what model routing looks like in the future. “We started this experiment expecting to measure how much Fable’s 2x premium would increase cost. We were surprised to find that Fable’s effective delegation actually decreased cost overall. It specified constraints and outcomes instead of spelling out the implementation, gave feedback instead of making fixes itself, and in most cases never touched the code at all. These are the habits of a good manager.” The industry is increasingly figuring out what it looks like to mix models together to be able to get targeted performance levels and optimal cost structures. Of course, the only way to get this is to have a deep understanding of the business problem you’re trying to solve and how to effectively route work to different models. If you’re in the applied layer - whether it’s customer support, legal, finance, or coding - this is how your harness will become a core area of differentiation.
@levie @joon_h_lee There’s a lot to still innovate on here. I don’t think we or anyone is close to figuring out the best way to orchestrate these yet
Again, another alpha of building your own harness & orchestrator.
Users praise the GPT-5.5 executor with GPT-5.6 advisor setup because it proves most tasks do not need frontier models and shows the value of combining cheaper models for cost savings.
Based on 3 visible X reactions from 5 accounts; directional sample.
Ask a question below.
Published answers will appear here.
Again, another alpha of building your own harness & orchestrator.