Sorry, I am going to ask this again.

This is exactly how a DAG works? So is the hype around things like Durable Execution, Temporal etc simply because something like Airflow is not more well known?

Sorry for the off-topic but I have been lately seeing a lot of hype around durable execution.

I still cannot figure out how this is any different than launching a workflow in something like Airflow. Is the novel thing here that it can be done using the same DB you already have running?

Haha I don't know if its a good test or not but I could not figure out why git pull was failing and Claude just went crazy trying so many random things.

Gemini 3 Pro after 3 random things announced Github was the issue.

I find the following way of expressing args awkward.

with engine: fn(args)

I would rather have

with engine: fn(args, engine)

This makes testing way easier.

I feel finding 1 persona makes sense since otherwise you will have a messy time trying to build too many things.

However, I also think selecting that single persona too early will hamper you more than messy building will.

So its a balance. You have to do a wider search in the beginning, which will involve a few too many demo builds but once you find that single persona that feels like it can lead to big growth you stick to it.

What kind of usecases does a screenshot CLI have?

Anybody know what is meant by 'injecting relevant metadata'. Where is it injected?

You typically add a lot of metadata with each chunk text to be able to filter it, and do to include in the citations. Injecting metadata means that you see what metadata adds helpful context to the LLM, and when you pass the results to the LLM you pass them in a format like this:

Title: ... Author: ... Text: ...

for each chunk, instead of just passing the text

I feel like this is how normal work is. When I have to figure out how to use a new app/api etc, I go through an initial period where I am just clicking around, shouting in the ether etc until I get the hang of it.

And then the third or fourth time its automatic. Its weird but sometimes I feel like the best way to make agents work is to metathink about how I myself work.

Odd, I've been stuck by how different LLMs and kids learn the world.

You don’t get that whole uncanny valley disconnect do you?

How so? Your kid has a body that interacts with the physical world. An LLM is trained on terabytes of text, then modified by human feedback and rules to be a useful chatbot for all sorts of tasks. I don't see the similarity.

If you watch how agents attempt a task, fail, try to figure out what went wrong, try again, repeat a couple more times, then finally succeed -- you don't see the similarity?

no I see something resembling gradient descent which is fine but it's hardly a child

> try to figure out what went wrong

LLMs don't do this. They can't think. If you just one for like five minutes it's obvious that just because the text on the screen says "Sorry, I made I mistake, there are actually 5 r's in strawberry", doesn't mean there's any thought behind it.

I mean, you can literally watch their thought process. They try to figure out reasons why something went wrong, and then identify solutions. Often in ways that require real deduction and creativity. And have quite a high success rate.

If that's not thinking, then I don't know what is.

You're arguing in circles. They don't "try to figure out reasons" because there is no concept of "trying", "figuring out" or "reasons".

> If that's not thinking, then I don't know what is.

How about actual thinking, you know, what humans and to a lesser extent animals do?

You just haven't added the right tool together with the right system/developer prompt. Add a `add_memory` and `list_memory` (or automatically inject the right memories for the right prompts/LLM responses) and you have something that can learn.

You can also take it a step further and add automatic fine-tuning once you start gathering a ton of data, which will rewire the model somewhat.

Perhaps it can improve but it can't learn because that requires thought. Would you say that a PID regulator can "learn"?

I guess it depends on what you understand "learn" to mean.

But in my mind, if I tell the LLM to do something, and it did it wrong, then I ask it to fix it, and if in the future I ask the same thing and it avoids the mistake it did first, then I'd say it had learned to avoid that same pitfall, although I know very well it hasn't "learned" like a human would, I just added it to the right place, but for all intents and purposes, it "learned" how to avoid the same mistake.

This is a silly definition of learning, and any way, LLMs can't even do what you describe.

A person is not their body.

The person is the data that they have ingested and trained on through the senses that are exposed by their body. Body is just an interface to reality.

That is a very weird and fringe definition of what a person is.

If you have a different life experience than what you had so far, wouldn’t you be a different person?

If you had one fewer leg, wouldn't you be a different person? Implication is not equivalence.

> It deeply resembles how LLMs learn and think

What? LLMs don't think nor learn in the sense humans do. They have absolutely no resemblance to a human being. This must be the most ridiculous statement I've read this year

I am sorry, but you are scoffing at the humanity of your kid; you know that, right?

My general experience has been that Gemini is pretty bad at tool calling. The recent Gemini 2.5 Flash release actually fixed some of those issues but this one is Gemini 2.5 Pro with no indication about tool calling improvements.

Ads. They created ads. Now (or eventually) they can charge app developers to be featured first for a specific use case.

How else would the company sell their product? and keep people employed.

Of course ads will be there and this is good. A bad thing would be if they took a bunch of traffic from google and then gave no way to promote your products.

That would lead to companies closing and layoffs and economy decline.

Just to clarify, my original comment was neutral about whether its a good or a bad thing. It was just a statement of observation.

Ads was always the end goal, they have an opportunity to become a bigger player than Google in the ad space.

Instead of the user wasting time, ChatGpt can come up with the recommendations.