Basically, the tool reframes conversations and tries to find the smallest moves the user COULD have made to have surfaced unknown assumptions for whatever problem they were solving.

The goal is to show the value of using AI as a reflective surface to search for "unknown unknowns" or "things YOU didn't know you needed to know".

-------------------------

The basic premise is this:

For any given AI conversation, the quality of the output (for the specified goal) depends on the context from which decisions can be made.

You can learn to surface assumptions (the AI's AND your own) and get better output from informed decisions. Best of all, when operating in this way, you have to actively engage the problem and strategy to accomplish this, so you don't lose understanding or creative agency.

When you iterate during problem definition or strategy planning, it's cheaper and more efficient, too.

For example:

[# of Planning Phase Iterations] x 1,000 tokens [# of Strategy Phase Iterations] x 3,000 tokens [# of Execution Output Phase Iterations] x 5,000,000 tokens

Usually when we are solving problems with this method, we one-shot the output even with local models like Qwen 3.6/3.8, spending FAR less time in the expensive execution phase.

---------------------------

Anyway, please have a look! Totally free, no signup, you just need to export conversations in specific formats and upload them.

This was made by myself and a few interns in a barn while doing indie game development ... and costs us money, so please don't abuse it. <3

Comments URL: https://news.ycombinator.com/item?id=50287887

Points: 1

# Comments: 0

Cool project!

I don't think that necessarily negates any conclusions, but, it doesn't help the author's case.

1. Do piddly algorithm type stuff that I've done 1000x times and isn't complicated. (Could take or leave this, often more work than just doing it from scratch)

2. Pasting in gigantic error messages or log files to help diagnose what's going wrong. (HIGHLY recommend.)

3. Give it high level general requirements for a problem, and discuss POTENTIAL strategies instead of actually asking it to solve the problem. This usually allows me to dig down and come up with a good plan for whatever I'm doing quickly. (This is where real value is for me, personally.)

This allows me to quickly zero in on a solution, but more importantly, it helps me zero in strategically too with less trial and error. It let's me have an in-person whiteboard meeting (as I can paste images/text to discuss too) where I've got someone else to bounce ideas off of.

I love it.

I prefer forgiveness over permission ...

I think a consciousness with access to a stream of information tends to drown out the noise to see signal, so in those terms, being able to "experience" real-time climate data and "instinctively know" what variable is headed in what direction by filtering out the noise would come naturally.

So, personally, I think the answer is yes. :)

To elaborate a little more - when you think of a typical LLM the answer is definitely no. But, if an AGI is likely comprised of something akin to "many component LLMs", then one part might very well likely have no idea how the information it is receiving was actually determined.

Our brains have MANY substructures in between neuron -> "I", and I think we're going to start seeing/studying a lot of similarities with how our brains are structured at a higher level and where we get real value out of multiple LLM systems working in concert.

https://en.wikipedia.org/wiki/Kolmogorov_complexity

https://en.wikipedia.org/wiki/Solomonoff%27s_theory_of_induc...

https://en.wikipedia.org/wiki/Minimum_description_length

Seems like these could be related, going to dive into this more! :)

Kurt Godel (or maybe Douglas Hofstadter, rather) would raise an eyebrow. :)

https://imgur.com/xanNjun

After you fix a lock-related bug for example, how do you deal with an open tab running a different version of your code that is erroneously misusing a lock?

You need to account for that when you release new code, yeah? Rename the lock maybe? Some other logic?

At least the Sudafed has acetaminophen in it ...

Alas, I do not. :(