I’m in this exercise right now, and I’m thinking about, how do I stay in the drivers seat. I think it’s a version of, bionics not robots.
Im trying to go back in time to when AI was more autocomplete than agent and write my code with assistance. Find the file, find where the code goes autocomplete the fix. Rather than one shot multi file changes do one at a time.
The bosses probably don’t want people spending 4 hours figuring out why upgrading a package conflicted with another package in weird ways or changed the API or other obscure things, so like, give troubleshooting 10 minutes, try to grok the code context, then prompt for a fix. Or prompt “show me where I need to look to fix this” and fix it yourself.
The question to really ask is what time scales are we talking about. Sitting down to do a task getting context and prompting code probably takes like what an hour, maybe 2 if you have to review it or fix something? If you add another hour to that, and really understand it, I think you’re not hampering your productivity all that much if at all in the aggregate.
The other thing I’ve always done is let myself get nerdsniped easily. Maybe multiple times a day if someone posts an error in chat I’ll give myself 5-10 minutes to look at logs/graphs/google. Keeps the job interesting but also I think keeps my mind flexible and into the details across a broad swath of tech.
I just don’t use any AI tooling for my home projects. Work pays for results so AI is basically mandatory to meet the deadlines - but home is for fun so I can take longer to produce hand crafted code.
> But what happens when that abstraction fails? as abstractions often do
One of the upsides to agents is that you can try out several abstractions instead of just one. You should absolutely be reading / spot checking the output (depending on context).
While skill loss is often the focus, there is also skill gain. I have learned new coding patterns or framework features through these tools.
On you main question, effort. Like everything, you have to use it or you lose it. I never saw my skill as a developer being the part where I peck at keys. It's the thinking and designing process, which I get to do way more of now that I don't have to peck.
Recommendation: build greenfield side projects, exercise building out all the parts. This will make you better at both being a developer and an agent manager.
I’m in this exercise right now, and I’m thinking about, how do I stay in the drivers seat. I think it’s a version of, bionics not robots.
Im trying to go back in time to when AI was more autocomplete than agent and write my code with assistance. Find the file, find where the code goes autocomplete the fix. Rather than one shot multi file changes do one at a time.
The bosses probably don’t want people spending 4 hours figuring out why upgrading a package conflicted with another package in weird ways or changed the API or other obscure things, so like, give troubleshooting 10 minutes, try to grok the code context, then prompt for a fix. Or prompt “show me where I need to look to fix this” and fix it yourself.
The question to really ask is what time scales are we talking about. Sitting down to do a task getting context and prompting code probably takes like what an hour, maybe 2 if you have to review it or fix something? If you add another hour to that, and really understand it, I think you’re not hampering your productivity all that much if at all in the aggregate.
The other thing I’ve always done is let myself get nerdsniped easily. Maybe multiple times a day if someone posts an error in chat I’ll give myself 5-10 minutes to look at logs/graphs/google. Keeps the job interesting but also I think keeps my mind flexible and into the details across a broad swath of tech.
I just don’t use any AI tooling for my home projects. Work pays for results so AI is basically mandatory to meet the deadlines - but home is for fun so I can take longer to produce hand crafted code.
> But what happens when that abstraction fails? as abstractions often do
One of the upsides to agents is that you can try out several abstractions instead of just one. You should absolutely be reading / spot checking the output (depending on context).
While skill loss is often the focus, there is also skill gain. I have learned new coding patterns or framework features through these tools.
On you main question, effort. Like everything, you have to use it or you lose it. I never saw my skill as a developer being the part where I peck at keys. It's the thinking and designing process, which I get to do way more of now that I don't have to peck.
Recommendation: build greenfield side projects, exercise building out all the parts. This will make you better at both being a developer and an agent manager.