And it sounds so knowledgeable and authoritative in its replies. And i like being told "great idea"...
OK, that is a joke i don't like it that much coming from a mindless agent.
But in the dialog it becomes so convincing that i struggle not to anthropomorphize it.
Remember "Her" with Joaquin Phoenix? i wont fall in love with it but i might entrust it with my root passwords?
OK, not scary at all. What kind of tasks do they tackle?
I would love i if they could scare my mother by making Max Headroom appear on her TV screen in the middle of her novela.
i started working with this two weeks ago, so im learning as i go (or should i say stumble and fall). Weird as it may sound what i found so trustworthy at the beginning, it sounded so rational and logic as it really knew better and i liked letting it do. Obviously it dis not go so well, and i had to correct a lot.
But i am learning, what can i say?
And yes, i gave it many commandements like "thouh shalt always test before releasing" and it sounded so convincing when it confirmed what an excellent idea that was that i was surprised at least -imagine that- when something did not go as planned on prod because of , well you know...
keeping context is a thing that they are bad at. For now, i admit, but they are.
Given a long haul goal with instructions and everything they will reinvent the wheel four times and one of those you will get a square.
Reminds me of that monkey paw wish thing. You look at your finished app. Looks beautiful, but its inner workings are a ball of confusion.
I don't use ChatGPT, but i've been using an agent with Claude Sonnet 4. My answer may not be useful to you, but i'll talk about my experience with that and hope it may help you.
So this AI Agent... It is much faster at doing code when given specific instructions. But it keeps loosing context on architecture, and i cant really let it build complex things with interdependencies that build on each other.
At times it feels like doing pair programming with a guy who is so crazy fast that im left behind with my head spinning, wondering how we just jumped from a hello world to a working thing that would have taken me ten iterations. And i get a bad feel when i then wonder how is this app doing what it does? because my agent cant explain it, and i would be stupid to believe what it hallucinated because it sounds really solid until you scratch the construction.
At the beginning i was almost euphoric about my new friend, now im sometimes disappointed, sometimes confused, but i am learning to give better, more concise instructions, to do smaller development jumps. It is tempting to set a long haul goal and let it do.
But, i think for now, even if it is much faster at the small things, it would be also faster to build a catastrophic spaghetti code nightmare if not used with great care.
OK, here's an update: i uploaded the dataset is on HuggingFace — 51k labeled headlines across 35 assets (commodities, FX, indices, crypto), with asset-specific inversion context. Source column separates human from AI labels.
huggingface.co/datasets/polibert/swik-sentiment-labels (http://huggingface.co/datasets/polibert/swik-sentiment-label...)
Happy to answer questions about the catalog methodology or the inference approach.
Also i implemented automated inversion hypothesis as a mechanism to confirm or reject.
Enjoyers of journey vs enjoyers of destination! What a brilliant idea.
I realize i enjoy the destination. And i await impatiently to finish the journey to enjoy that place that was in my minds eye all along during the journey.
i like developing with my agent because it brings me there incredibly fast.
I must agree on this. And it opened my eyes. I realize that I enjoy the destination more than the journey. I'm impacient, and have that destination in my minds eye all the time and my Ai agent is getting me there at a crazy pace.
Enjoyers of journey vs Enjoyers of journey destination! you gave me something to think about.
I'm loving the experience and i also realize that this part of me, the one which could write code is obsolete. Completely. Utterly obsolete.
OK, so first i need to admit that i am not the best programmer, but i've been at it for 27 years.
These past months I've been working with two agents developing two things practically in parallel.
And i've experienced the fastest, most motivating development sessions i ever had.
Together with these two agents i was able to build two very complex systems that use all sorts of data gathering, then ETL into a format that can be queried and maintained, and it all ends up in some awesome web UIs.
I used Them not only to write code, but to do the design and architecture, discussed the front end, the business reqs.
And what i can say, is that it felt like a conversation with a crazy fast person who did everything i needed in seconds.
AS a tech guy i know what i want and i know how to describe it. That helped A LOT!
I know when we lost context and yes, there were stupid consequences that we had to fix.
But my impression is that many of these things i see criticized here refer to the people using it, less than to the AI and its output.
From my point of view, the output is what i wanted, only 250x faster than i ever expected.
And for the critiques targeting the AIs, after this i am sure that they will learn to fill in all those gaps.
We will not be criticizing then. By then my only possible job will be to translate somebody's business reqs for an agent to implement as i speak.
Infrastructure management mostly — cron scheduling, DB migrations, nginx configs, log analysis. Things I know how to do but that are slow to type out.
But the learning is there:
I've used it to go deep on PostgreSQL query planning and indexing in a way I wouldn't have bothered with before.
The risk, in my opinion was the opposite of I'd expected — not learning less, but a lot of shallow things giving an impression of learning which in effect isnt there.
Look! i built this powerful thing. 60.000 Lines of coded business logic in a week!
On the surface i have something impressive to show. People admire it, and i end up believing that i did it. This is not to say that i did not learn - i did, but my learning was not as impressive as the result would make you believe.
I haven't tackled payments, but I've run an agent with SSH access to a production server and real API keys for a few weeks. The trust question you're circling ("would you trust an AI with $500") is the interesting part. My answer so far: yes for reversible actions, not yet for irreversible ones. Deleting a file, sending an email, making a payment — these need a different approval model than reading a database or running a query. The hard problem isn't capability, it's building infrastructure that distinguishes "can do" from "should do without asking.
And i want to build an agent capable to do automated investment. so, to the question "has" anyone...?" i believe yes, my role model is Jim Simons from Renaissance. He did.
I think you have a point. The credential part feels like a solved problem — auth-proxying has been around for a while. What seems genuinely new to me is the approval layer, the idea that a human should confirm before a sensitive action actually executes. I'm not sure that's covered by tokenizer or SSO proxy, but I could be wrong. Is that the real differentiator here, or am I missing something?
A problem i have is that the agent's mental model of the system im building diverges from reality over time. After discussing that many times and asking it to remember, it becomes frustrating.
In the README you say the agents memory persists across runs, would that solve said problem?
Also, I had to do several refactorings of my agent's constructs and found out that one of them was reinventing stuff producing a plethora of function duplications: e.g. DB connection pools(i had at least four of them simultaneously).
Would AXE require shared state between chained agents? Could it do it if required?
YES!
happens to me all the time in things big and small. At work, at home, with the kids, my wife, and their birthday presents.
I once talked to a somewhat famous writer who told me this very thing.
He said his worst critic was his inner demon biting him at every thought, every phrase, questioning his wording, waiting for the greatest possible idea, discarding all that was not breathtaking enough.
Why do we have to be great all the time? Who is telling us to be best?
And i know that in writing this i am pruning myself again trying to find the best words here.
Imagine that: i want enough points for karma to be able to post here my greatest idea. Which ironically enough, is the best greatest idea i had in a loooong time, and the moment i want to share it i must wait to be found good enough and worth to be heard.
I guess the only thing we can do is to disconnect our feeling of self worth from outside signals and be happy with the little things that made us smile when we did not know nor care about other peoples opinions.
The "deny list is a fool's errand" framing is exactly right. I've been running an AI agent with broad filesystem and SSH access and the failure mode (so far) isn't the agent doing something explicitly forbidden — it's the agent doing something technically allowed but contextually wrong. git checkout on a file you meant to keep is the classic example.
The action taxonomy approach is interesting. Curious whether context policies work well in practice — what does "depends on the target" look like when the target is ambiguous? E.g. a temp file in /opt/myapp/ that happens to be load-bearing.
The stale state problem is real and underappreciated. I've been running browser automation through OpenClaw and the failure modes you describe — modal appears after screenshot, dropdown covers the target element — are exactly what causes silent failures that are hard to debug. The agent "succeeds" from its perspective because it acted on the last known state.
The freeze-then-capture approach is interesting. Curious how it handles pages with aggressive anti-bot detection that fingerprints headless Chromium forks — that's the other failure mode I keep hitting.
This is directly useful for financial data monitoring. I've been thinking about watching specific elements on energy report pages (EIA weekly inventory releases, OPEC statements) rather than scraping the full page. The element picker + RSS output is exactly the right interface for that — pipe the change event straight into an NLP pipeline without the noise of a full page diff.
The RSS question: yes, RSS is useful precisely because it's composable. It works with anything. Direct alerts are convenient but RSS is infrastructure.