> Please carefully review (whatever it is) and list out the parts that have the most risk and uncertainty. Also, for each major claim or assumption can you list a few questions that come to mind? Rank those questions and ambiguities as: minor, moderate, or critical.
> Afterwards, review the (plan / design / document / implementation) again thoroughly under this new light and present your analysis as well as your confidence about each aspect.
There's a million variations on patterns like this. It can work surprisingly well.
You can also inject 1-2 key insights to guide the process. E.g. "I don't think X is completely correct because of A and B. We need to look into that and also see how it affects the rest of (whatever you are working on)."
Of course! I get pretty lazy so my follow-up is often usually something like:
"Ok let's look at these issues 1 at a time. Can you walk me through each one and help me think through how to address it"
And then it will usually give a few options for what to do for each one as well as a recommendation. The recommendation is often fairly decent, in which case I can just say "sounds good". Or maybe provide a small bit of color like: "sounds good but make sure to consider X".
Often we will have a side discussion about that particular issue until I'm satisfied. This happen more when I'm doing design / architectural / planning sessions with the AI. It can be as short or as long as it needs. And then we move on to the next one.
My main goal with these strategies is to help the AI get the relevant knowledge and expertise from my brain with as little effort as possible on my part. :D
A few other tactics:
- You can address multiple at once: "Item 3, 4, and 7 sound good, but lets work through the others together."
- Defer a discussion or issue until later: "Let's come back to item 2 or possibly save for that for a later session".
- Save the review notes / analysis / design sketch to a markdown doc to use in a future session. Or just as a reference to remember why something was done a certain way when I'm coming back to it. Can be useful to give to the AI for future related work as well.
- Send the content to a sub-agent for a detailed review and then discuss with the main agent.
Going from a high tax state to a low tax state to purchase goods is not substantially different than going from a state with strict anti-abortion laws to a state with very pro-abortion laws to get an abortion. One is economic, one is healthcare, both boil down to "I shouldn't have to tell the government what I do outside of that government's jurisdiction." I'd rather people have the freedom to vote with their wallets and feet.
Even taking states out of the equation, if I live in a city with a city-specific sales tax, that city doesn't suddenly get the right to lay claim to all my economic activity whether in that city or elsewhere.
That tax is a "use" tax. It is basically for having/using things in the state that you didn't pay state sales tax on.
You don't have to tell the state why no sales tax was paid--maybe you bought it in another state but maybe you bought it at a garage sale or from someone on Craigslist or something like that that doesn't collect sales tax.
The use tax is only legal if it is complementary to the sales tax (which means that the total you pay cannot be more than the sales tax rate) so that if you did buy it out of state and paid sales tax in that state your state can only charge you the difference between what the sales tax would have been in state and what you paid to the other state.
That does mean that you will have to tell the state where you got it if you want to get the reduced use tax rate, but as a practical matter most people only pay use tax on items that they have to tell the state about anyway, such as cars, where they will be telling the state that information even if no use tax is owed.
Nope - though I’ll take it as a compliment either way. It’s a problem I’ve been sitting with for a while, so the answer came out more formed than I expected. You disagree?
Its actually a pretty good idea/framework for writing commit descriptions, especially for smaller changes that don't have any nuances to note in the commit
Why only small changes tho? I think it can also work with larger changes if you commit more regularly. And with agentic coding or even with autonomous agentic coding, you need to do it regularly and create these contextual checkpoints, no?
AI writing sucks because it doesn't have a voice. It's not trying to say anything. Human writers are interesting because they offer a unique perspective from their lived experience.
It also struggles to maintain deep coherence. This is all probably related. It might be very hard or impossible to have deep coherence without human-like goals, memory, or sense of self.
I don't think lived experience matters too much to me.
In some sense, AI has very unique "lived" experience, which is what creates the voice it uses ("doesn't have a voice" seems like an impossibility to me by definition).
I find AI very "human-esque", and its "self-reported" phenomenology is very entertaining to me, at least.
I also think AI writing might feel trashy also because most human writing is trashy.
Have the LLMs generate tests that measure the “ease of use” and “effectiveness” of coding agents using the language.
Then have them use these tests to get data for their language design process.
They should also smoke test their own “meta process” here. E.g. Write a toy language that should be obviously much worse for LLMs, and then verify that the effectiveness tests produce a result agreeing with that.
reply