plastic041

> semantic trick

That's what I wanted to say! Thank you.

It still would be a self promoting, which is still an ad.

I do think it's just an ad. Also it's a bad kind of one because 1) it disguises itself as a tip 2) makes people to think if it's an ad for Raycast or other services, when actually it's just promoting itself.

This "ad" is not exactly new. Looks like MS thinks it's a "tip" rather than an ad. I don't know if Raycast team even knows about this.

https://github.com/PlagueHO/plagueho.github.io/pull/24#issue... Copilot has been adding "(emoji) (tip)" thing since May 2025. GitHub copilot was released in May 2025, so basically it has had an ad since beginning.

There are 1.5m of these things in GitHub. https://github.com/search?q=%22%3C%21--+START+COPILOT+CODING...

Here are some of them:

https://github.com/johannesPP/FS-Calculator/pull/2

> Connect Copilot coding agent with Jira, Azure Boards or Linear to delegate work to Copilot in one click without leaving your project management tool.

https://github.com/sharthomas645-tech/HybridAI-Next-React-Vi...

> Send tasks to Copilot coding agent from Slack and Teams to turn conversations into code. Copilot posts an update in your thread when it's finished.

Looks like MS really want to "give tips" about their new integrations.

edit: I think it's an ad too. Everyone would think so, except for MS.

This is FIM(fill in the middle) + comments with extra "compile" step.

How can people believe that you are respecting bot detection in production when your software's README says it can "Avoid detection with built-in anti-bot patches"?

robots.txt is the most basic access restrictions and it doesn't even read it, while faking itself as human[0]. It is about bypassing access restrictions.

[0]: https://github.com/lightfeed/extractor/blob/d11060269e65459e...

> Avoid detection with built-in anti-bot patches and proxy configuration for reliable web scraping.

And it doesn't care about robots.txt.

> This isn’t a generic chatbot. It’s a custom-built voice agent that answers his phone, knows his exact prices, his hours, his policies, and can collect a callback when it doesn’t know something.

This is 2026's most generic chatbot.

I wanted to know how to make softwares with LLM "without losing the benefit of knowing how the entire system works" and "intimately familiar with each project’s architecture and inner workings", while "have never even read most of their code". (Because obviously, you can't.) But OP didn't explain that.

You tell LLM to create something, and then use another LLM to review it. It might make the result safer, but it doesn't mean that YOU understand the architecture. No one does.

> Since my main goal was to learn, I decided to do it "the right way". This means I didn’t want to rely on Replit or Lovable where the infra part is obfuscated. I wanted to deal with that complexity myself.

I expected OP to actually 'learn' devops, but what they did was just asking LLMs to do everything.

Also...

> 180+ paid $2 for a dino

People pays $2 for an image of dinosaur with human face?

Is this an openclaw alternative that is installed on my mac but runs on their cloud? Or just a VDI?

It's difficult to understand what this is because its name is "Personal Computer", and it seems like their definition of Personal Computer is very different from everyone else's.

Also it's funny that it shows making a revenue report with their brand template. AI can replace HR jobs but they still have to make reports for noble executives? They are basically saying "We won't replace CEOs/executives".

That's Duration!

    const D = Temporal.PlainDate.from("2020-06-16");
    const t = Temporal.Duration.from({ day: 1 });
    const v = D.add(t) // 2020-06-17

https://developer.mozilla.org/en-US/docs/Web/JavaScript/Refe...

It's ironic to debate whether 'clean rooming' or rewriting violates licensing laws when LLMs clearly violate all of them.

Also no one can prove that whether LLMs referenced original code or not, because LLM companies don't disclose what data they used. I'm pretty sure that well-known open source projects such as chardet has been included in the Claude dataset, but Anthropic won't say anything about this.

The fact that humans can use this feels like a side effect. The developer says it's "built for agents first" and "AI agents would be the primary consumers of every command, every flag, and every byte of output"[1].

[1] https://justin.poehnelt.com/posts/rewrite-your-cli-for-ai-ag...

It's built for agents first, unfortunately.

https://justin.poehnelt.com/posts/rewrite-your-cli-for-ai-ag...

> Deathbot Incongruence Anxiety

This sounds like a term from an Arthur C. Clarke novel. Also reminds me of Urasawa Naoki's Pluto.

> Information Utility Burnout

These days, every time I search for something, I have to use 100% of my brain just to work out which results are slops and which are not, even on Kagi. A few days ago, I had to search for something on Google without an adblocker. It was a remarkable experience. Like, 60% of my screen were ads or AI slops.

It can't read my mind. This means that I have to say "I need to buy eggs" out loud in front of the machine (or in another room, depending on how good the microphone is). I'd rather just say "Hey Siri, remind me to buy eggs" to my phone.

It's funny that this is their first ad on ChatGPT, yet they've included paid tier (Go, 8$/month).

But the AI agent still needs to determine which tool is necessary to mint the warrant. What happens if the agent makes a mistake when making warrant?

It hasn't been actively maintained, but it is still a good crate. Also it has good document unlike other similar crates. I loved this community tutorial: https://github.com/sidwellr/schotter

This is an advertisement for a 'tenuo warrant'. So, I read its document[0]. Put simply, it works like this:

1. A person orders an AI agent to do A.

2. The agent issues a tenuo warrant for doing A.

3. The agent can now only use the tool to perform A.

The article is about that 'warrant' can now be used in case of an incident because it contains information such as 'who ordered the task' and 'what authority was given'.

I get the idea. This isn't about whether a person is responsible or not(because of course they are). It's more about whether it was intentional.

However... wouldn't it be much easier to just save the prompt log? This article is based entirely on "But the prompt history? Deleted."(from the article) situation.

[0]: https://tenuo.dev/concepts

> They explicitly state that the problem is you don't know which human to point at.

The point is "explicitly authorized", as the article emphasizes. It's easy to find who ran the agent(article assumes they have OAuth log). This article is about 'Everyone knows who did it, but did they do it on purpose? Our system can figure it out'

> a bibliography (a list of relevant works but not necessarily cited)

Didn't know that there's difference between bibliography and cited work. thank you.

The video shows a user asking Prism to find articles to cite and to put them in a bib file. But what's the point of citing papers that aren't referenced in the paper you're actually writing? Can you do that?

Edit: You can add papers that are not cited, to bibliography. Video is about bibliography and I was thinking about cited works.

> HN users that have settled on the belief that if something is done using AI it is "lazy slop" and it needs to be shunned!

Honestly, I used to be one of them. I recently saw a great library (atcute) that changed my opinion. I think most AI sceptics haven't had this experience. They saw AI slops and set their opinion: AI-generated codes are bad. I can't really blame them, though, because there are so many of AI slops.

> anyone who is not incorporating it in some way (workflow or actual end product) is just holding themselves back.

It's true. However, I think people who create AI slops are worse than those who don't use it. They are diligently making this world a worse place.

It's likely long tail. I don't think good Show HNs are gone. They are still there, but they are being overwhelmed by lots of low quality submissions.

In the second report, Daniel greeted the slopper very kindly and tried to start a conversation with them. But the slopper calls him by the completely wrong name. And this was December 2023. It must have been extremely tiring.

related: cURL stopped HackerOne bug bounty program due to excessive slop reports https://news.ycombinator.com/item?id=46678710

"Support" says to open an issue on GitHub if I need help. You should remove the line since this looks like a closed source project.