this is the way. every protocol will have its own cli and agentic interaction will be commoditized. then the bottleneck is trust for delegating real capital.

this will happen more over time. agents keep operating with money without guardrails. no trust can be given, for now.

everyone building wallets for agents is focusing on the wrong problem.

how we interact with products and infrastructure it’s changing fast. there is an existential need to adapt and provide value for the world of tomorrow. what is currently happening in software eng. will happen in every field including finance.

the internet will shift towards agents navigating a huge API space settling in onchain rails. but, how could agents interact safely with money on behalf of humans in this world?

this is the way. ai agents will not disrupt finance until there are mechanisms in place to trust their actions before onchain settlement.

recommended read. llms tend to fall heavily into sycophancy creating compounding problems in software systems. you need to understand the underlying reasoning of the implementation to make sure llms write correct code. the more surface to implement the more prone to errors

everyone is building a harness, for now.

quite obsessed with evals for harnesses / model on custom tasks. deep rabbit hole to go into and really makes a difference in the quality of an agentic system.

crypto tax companies are cooked, very unreliable with crazy pricing. shared my personal situation with docs, contracts etc to my local llm and with Nansen 🧭 cli for all the onchain activity. sharing with my accountant now for review. all this done for a fraction of the cost,

this is one of of the latest and most exciting breakthroughs in the llm space. this could open many possibilities if scaled properly.

the more you work in agentic systems the more you know is not about the model. we are heading towards custom harnesses curated for different areas. also its mportant to know what to optimize your harness for.

privy is building one of the best foundations for agent authorization, but authorization and intent enforcement are different layers. one validates who can sign, the other validates what should be signed. agents managing real capital need both.

“time turns some idea or plan into a commitment and a commitment into something that can shelter and grow other people.” some things just require time, even when ai is accelerating software creation.

i also had the same conclusion a few months ago. working fist in the evals aligns your coding agents for success when the actual implementation begins. also you have a very objective way to track progress on metrics you care about.

our product is not even announced and we are already getting thousands of organic downloads in less than a month. still so early

this is awesome, until now wallet security for agent was very fragmented with custom implementations everywhere. now there is standard to provide secure wallet access to agents, fully open source.

llms will breach into new domains by bringing mastered capabilities in their knowledge, i.e. coding, and adapted to new domains. coding will rule how llms interact in any domain and not by relying in pure reasoning. also, as a side effect new languages for agents will appear.

using Conductor has been a really great increase in productivity lately. also the ux incentivizes for slop reduction and has a great review experience as a human in the loop. very recommended.

this is awesome, time to give it a try