Obviously you should also use Claude to consume those 50 pages. It sounds cynical, but it's not. It's practical.
What I've learned in 2 years of heavy LLM use - ChatGPT, Gemini, and Claude, is that the significance is on expressing and then refining goals and plans. The details are noise. The clear goals matter, and the plans are derived from those.
I regularly interrupt my tools to say, "Please document what you just said in ...". And I manage the document organization.
At any point I can start fresh with any AI tool and say, "read x, y, and z documents, and then let's discuss our plans". Although I find that with Gemini, despite saying, "let's discuss", it wants to go build stuff. The stop button is there for a reason.
I use an agents.md file to guide Claude, and I include a prominent line that reads UPDATE THIS FILE WITH NEW LEARNINGS. This is a bit noisy -- I have to edit what is added -- but works well and it serves as ongoing instruction. And as you have pointed out, the document serves as a great base if/when I have to switch tools.
I have a lot of experience, low and high level. These AI tools allow me to "discuss" possibilities, research approaches, and test theories orders of magnitude faster than I could in the past.
I would roughly estimate that my ability to produce useful products is at least 20x. A good bit of that 'x' is because of the elimination of mental barriers. There have always been good ideas I had which I knew could work, but I also knew that to prove that they could work would take a lot of focus and research (leveling up on specific things). And that takes human energy - while I'm busy also trying to do good things in my day job.
Now I have immensely powerful minions and research assistants. I can test any theory I have in an hour or less.
While these minions are being subsidized in the wonderful VC way, I can get a lot of done. If the real costs start to bleed through, I'll have to scale back my explorations. (Because at a point, I'll have to justify testing my theories against spending 2-300$.)
To your questions, I'm usually a solo builder anyway. I've built serious things for serious companies, but almost always solo. So that's quite a burden. And now I'm weary of all that corporate stuff, so I build for myself. And what a joy it is, having these powertools.
If I were in a company right now, I could absolutely replace a team of 5 people with me + AI... assuming the CTO wasn't the (usual) limiting factor.
It's really interesting how delusional people here can get when their livelihood depends on it. It's a game changer guys. I've been working professionally for 12 years. Big companies, small companies, freelance, startup CTO nowadays. It's multiplier. It gives me superpowers. If you don't feel the superpowers, you're either missing out or in denial. Embrace agentic coding.
If you fully measure the output (benefit) vs cost, the numbers don’t look so bad.
For example, it is known that nutrient value in produce drops at an astonishing rate over time; so having locally grown food that you can pick and eat immediately means you’ll get vastly more benefit, beyond just calories and fiber.
Also, when supply chains get disrupted and your grocery has empty shelves, you still have good, healthy food.
You’re also reducing transportation effects, which is to say you are having a less negative impact on the environment.
Most of what we put prices on are ignoring real costs.
I have a secret theory that the inherent depletion of some as yet unidentified "total nutritional value" of the foods we eat, due to mass farming and fertilizer reliance, plays some part in the American and global obesity crisis.
It's probably more of an issue in the pre-obesity stage, but since man does not live by bread alone any more than man lives by calorie alone, and given that a person can die of malnutrition with a full stomach, for instance by eating only rabbit or fish, I imagine that at least part of what causes the insatiable hunger or lack of satisfaction from eating that leads to obesity must surely be that there are some nutrient profiles that are missing from most of the food we have available.
Bringing necessities (water, food, energy) local is worth subsidizing. For those who doubt, just look at current events. Two morons with the right levers can upend countless critical processes.
I have no idea how that person is doing it, but I suspect it could be using osascript. Here's how I do it from my homegrown Go bookmark tool:
const fetchTabsScript = `
tell application "Brave Browser"
set output to ""
repeat with w in windows
repeat with t in tabs of w
set output to output & (URL of t) & "|||" & (title of t) & "\n"
end repeat
end repeat
return output
end tell
`
func GetOpenTabs() ([]Tab, error) {
cmd := exec.Command("osascript", "-e", fetchTabsScript)
output, err := cmd.Output()
// ...
}
US capitalism (aka, powerful financial entities driving policy).
To be fair, not all people in business or government prioritize "the all-mighty dollar" over everything else. Unfortunately, those who don't usually have principles; those who do often are willing to break rules. This is not an even match.
It's just an appellate court ruling, not the summary execution of Bernie's last faithful warrior. It can't even set precedent since the opinions are unpublished.
Fox News and Trump still routinely say it's a hoax. And their devotees repeat that line in one breath, and in the next breath say, "wow, we just set a new high temp record in January!"
What I've learned in 2 years of heavy LLM use - ChatGPT, Gemini, and Claude, is that the significance is on expressing and then refining goals and plans. The details are noise. The clear goals matter, and the plans are derived from those.
I regularly interrupt my tools to say, "Please document what you just said in ...". And I manage the document organization.
At any point I can start fresh with any AI tool and say, "read x, y, and z documents, and then let's discuss our plans". Although I find that with Gemini, despite saying, "let's discuss", it wants to go build stuff. The stop button is there for a reason.
reply