I have a (rapidly) growing conviction that "best practices" in software are just artifacts of product limitations. We called them best practices because software couldn't adapt to all the bespoke feature requests. AI removes that constraint, and it's the single biggest impact AI will have on the industry. All software will become malleable. It will bend around your business rather than you trying to figure out how to fit your business into the software. Paulo didn't change his fencing business to fit the software he was using... he changed the software to fit his business. IMO this is as significant a platform shift as the move from on-prem to SaaS.

Incentives are the strongest growth lever in DeFi. The best campaigns generate growth that outlasts the rewards. The difference isn't a bigger budget. It's better design. Our new guide on campaign best practices ⤵︎

Just met with one of our engineering leaders. Some takeaways about AI engineering best practices + more: 1) Spec writing and strong reading comprehension are two of the most valuable skills in ai engineers today. 2) Being hyper structured and opinionated in engineering workflows is how you get probabilistic models to behave deterministically when you want them to and also get models to spend tokens efficiently. 3) Creating a standardized schema/metadata on markdown files in your workflows allows you to make non-software tasks verifiable which allows you to close the agent loop more successfully. 4) One of the bigger behavioral changes in knowledge work is learning to thoughtfully structure/organize your files like good engineers have always done to get the least entropy from models. 5) Building a strong immune system around markdown files is important. As a workflow evolves and gets more reps it’s easy for specs to get bloated with conflicting guidance/unnecessary rules. Hermes agents solves this with a thin memory layer. There’s still a lot of optimization to be done with memory/markdown autophagy. 6) The key ingredients of our engineering process are CLI + deeply opinionated folder/file system + markdown metadata + coding agents + linear as source of truth. 7) Our mental model is always how can we make sure the agent has one way to do things and can validate its output.

.@YaleClubNYC @BernardJTyson @dkberman @KPMemberService "The Kaiser model is spread all over the country ... best practices are passed on fluidly ... the challenge is who stays ahead of the curve"