I settled on a knowledge graph in Postgres and downloading/storing the source documents so it could iterate on past results without more scraping or network calls.

This blog post helped me understand security analysis in this context! A lot of the important systems around malware analysis or large scale system security (the parts people really care about) clicked for me. So thanks for writing it.

Anyways I hope we can find some pattern to converge on with this wrt "facts management" since I feel this is currently something a lot of people and LLMs are struggling with. In practice current LLMs working with episodic memory feels similar to a grandparent with dementia scrawling things down in notebooks, crossing things out, and getting very confused.

Comments URL: https://news.ycombinator.com/item?id=48586626

Points: 3

# Comments: 0

It's a little slow sometimes, but it's the first time I've felt like I have an independent agent that can handle things kind of.

The only two things I did were 1. Ask it to create a Monero address so I could send it money, and have it notify me whenever money is sent to that address. It spun up its own monerod daemon which was really heavy and it ran out of space. So I had to get it to use the Monero wallet instead, but had to manually intervene to shut down the monerod daemon and kill the process and restart openclaw. In the end it worked and still works. 2. I simply asked it "@ me the the silver price every day around 8am ET" and it just figured out how to do it and schedule it. To my understanding it has its own cron functionality using a json file. 3. Write and host some python scripts I can ping externally to send me a notification

I've had it done other misc stuff, but ChatGPT is almost always better for queries, and coding agents + Zed is much better for coding. But with a cheap enough vm and using openrouter plus glm 4.7 or flash, it can do some quirky fun stuff. I see the advantage as mainly having control of a system where it can have long term state (like files, processes, etc) and manage context itself. It is more like glue and it's full mastery and control of a Linux system gives it a lot of flexibility.

Think of it more as agent+os which you aren't getting with raw Claude or ChatGPT.

I've done nothing that interesting with it, it's absolutely a security nightmare, but it's really fun!

Does this handle the case where there are longer-running activities that have low CPU usage? Couldn't these be canceled during scalein?

Temporal would retry them, but it would make some workflow runs take longer, which could be annoying for some user-interactive workflows.

Otherwise I've seen needing to hit the metrics endpoint to query things like `worker_task_slots_available` to scale up, or query pending activities, pending workflows, etc to scale down per worker.

The conditions that lead to having two tokens pointing to the same functionality should be prevented, but in this case it is a "de facto" alias which no amount reasonable amount of labor could fix.

In the rationale for this that I can find [1], a maintainer says the following:

> I'm inclined to say we should do it, even though it will cause some disruption.

They also say an alternative is to "accept the status quo", which is exactily what they should be doing. I can't find maintainers giving a compelling reason not to support this status quo of `long-description` as an alias to `long_description` besides "simplifying code." Code simplification should never take precedence over massive breakage of compatibility.

[1] https://github.com/pypa/setuptools/pull/4870#pullrequestrevi...

> ... evil cannot by itself flourish in this world. It can do so only if it is allied with some good. This was the principle underlying noncooperation—that the evil system which the [British colonial] Government represents, and which has endured only because of the support it receives from good people, cannot survive if that support is withdrawn.

If you are a good person working for the big G...

The first "line photo" is the right-most column of pixels on that photo. The next photo is the second-to-the-right column, etc. This way the winner can be determined as the line first photo that has the contestant's torso in it.

I'll click "Sign in to Downpour", it will bring me to a "Open link in App?" page, I press "Open", and then it brings me to a "Downpour -- make a game" page and I click open again which brings me to the app store. The app is installed on my phone.

So to me it feels like playing against a soulless vector database rather than something engaging and well-crafted. I think what gives me this impression is that things are commonly related to each other using words rather than their meaning -- getting from "pirate" to "captain crunch" to "serial killer" is obviously following lines of language rather than the core concepts that relate objects. This is directly opposed to the actual act of crafting which is 100% rooted in the material world and has no relationship to language.

Maybe I'm losing my imagination, but doing it like you suggest, creating challenges, is makes it more fun. I think I'm just tired of thinking in language.

I'm also seeing a lot of my favorite game creators on twitter enjoying the toy and I'll trust their taste over mine :)