Experiment, experiment, experiment.
Treat the AI like you would a new hire at your business, think about how you would verify their task quality at minimal effort.
Those that deeply understand what their role is at a company and can see how an AI might do it (you don’t necessarily need to know how to build it) will fare far better than those that just execute a process.
The goal is to remove the human from the loop, not engineer the human into the loop.
Afternoon dev and wings with @GeoffreyHuntley and the harsh reality is that people need to adapt to AI far more rapidly than they are, patience is waning and we are coming up to an inflection point where those that get it are going to accelerate away at an even more rapid rate.
@GeoffreyHuntley You’re nicer than I am, I think FUD is unfair though. The days of uncertainty and doubt are behind us, at this point if you’re not learning AI it’s a decision (at an individual and corporate level)
@dexhorthy@erd0xbc@Mnilax@RMB@dex what do you think the calculation looks like. Claude code with max subscription versus something like Pi which doesn’t have the bloat but you pay API prices?
Interesting. How does the system identify an action that is permissible versus one that is not.
Let’s say I’m having a Claude session investigate a production issue. It wants to read information from a sensitive database, how does the system identify if that’s a permissible tool call or not?
1. Thank you for sharing how much time you’re spending on the setup of these capabilities. A lot of people don’t realise you need to spend decent effort to build something reliable enough to unlock 10x velocity.
2. Why video over screenshots? Just wondering about the storage tradeoffs and the ability for subsequent downstream agents to interpret the objects?