jarboot

Incredible

This is amazing!!! It just makes sense. And its just how you would want to use a e reader.

I encountered this with trying to have LLMs populate facts about electoral campaigns. Like when a candidate drops out, when endorsements happen, but also if a candidate is un-endorsed or drops and rejoins. It also needed to handle if any of these facts were incorrect.

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.

I disagree, the approach works well in a legacy project, since there are structures and standards that already exist, which them model can draw from (if you aren't more explicit about it in AGENTS.md)

I think this is a good usecase for temporal + pydantic-ai

I spun up an Debian stable ec2 vm (using an agent + aws cli + aws-vault of course) to host openclaw, giving it full root access, and I talk to it on discord.

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!

Hate to be the guy in the comments complaining about the css, but the sides of the text of this article are cut off. It looks like I'm zoomed in, and there's no way I can see the first few columns of the text without going to Reader view. I'm on a modern iPhone using safari, accessibility settings font larger than usual.

> Autoscaling is configured via CloudWatch alarms on CPU usage: > Scale-out policy adds workers when CPU > 30%. > Scale-in policy removes idle workers when CPU < 20%.

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.

Temporal.io has been good for orchestrating agentic workflows, or workflows in general

I'm looking forward to the day that LLMs automatically put knowledge like this into Anki or something like it.

godel terminal, prosperous universe

Love to see a midwest/great lakes business address :)

"Needs to be gone" is the operative phrase here. An alias of `description-long` to `description_long` has no specific technical need to be removed.

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.

The current approach of the maintainers terrifies me -- de facto standards should be respected. Even if something is invalid like `description-file`, if it is present in 12k repos it should raise a warning and not break anything.

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...

From Gandhi's commentary on chapter 1 of the Bhagavad Gita:

> ... 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 entire photo is the finish line. Look at the color of the ground -- it's cream, the color of the lines on the track, while the track is blue. Each vertical line of the photo is taken in the same position on that finish line.

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 don't think anyone has access to view the notion page, you might need to change permissions.

The irony of this comment and "Strangers on social media assume you are American and get mad when you correct them." in the essay

I really want to sign up and share a creation, but when I do either sign up or sign in, it gives me a firebase url that just redirects me to the app store. I can't find any way to sign up.

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.

I tried your challenge to create pizza. My goal is to get some kind of food, but combining combinations of water, plants, fire, etc are way more likely to produce dragons and universes. I eventually got to chestnut which got to bread, but it was a lot easier to get to "Toast Toast Toast" or "Chestnutzilla" or "Treasure" + "Toast" = "Pirate". I finally got "Tostzilla" which has a pizza emoji, and then "lunch", and "breakfast", and "party"+"toast"="celebration" ?? but it feels random and illogical at some point I just gave up.

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 :)

The request looks like "https://neal.fun/api/infinite-craft/pair?first=Phoenix&secon..." so it's probably typically caching the combination of phoenix+seeds but if there is no cache entry it would use llama to make up something. If there's a lot of attention on the site the llm service might be down or overloaded. And given the exponential/factoral (?) amount of combinations this may be reached surprisingly quickly. Just a guess.

As an aside, the game is technically interesting, being a really simple example of using llm generation for game mechanics. But it is not engaging at all and feels nonsensical to me, especially when compared to little alchemy https://littlealchemy2.com/.

I'm not trying to be negative and this isn't a dig on creativity of the wonderful Neal but more points to the immaturity of llms applied to games, maybe to my overexposure to chatgpt, and maybe a prediction that human touch will always be required to make something entertaining. I'm curious how llms will fit into an engaging game experience in the future.

I've been thinking about making a cross-platform mobile app but don't want to think about react native, touch javascript, or fiddle with xcode any more than I have to.

Is it accurate to think that I could instead use godot to create a cross-platform app to eliminate complexity from react native while creating something that is performant/native across ios/android?

Largely? Pharmaceutical companies only make up 3.8% of revenue according to the document you posted.

What fixed this for me was disabling siri

If I want to create a task that runs even after the function returns, ie "async def f(): asyncio.create_task(coro=10_second_coro.run()); return;" is there any way to mitigate this? Function-scoped set of tasks?

Loving the simplicity of a typescript frontend + rust backend

typing 'hidden test' before launching the ball still activates the same cheat as the original :)

tiktok audio is not off by default. But it's right in the idea that some people will have the audio off, and cc means you can consume the content in either case.