To quote the guidelines[1]:
> Please don't post insinuations about astroturfing, shilling, brigading, foreign agents, and the like. It degrades discussion and is usually mistaken. If you're worried about abuse, email hn@ycombinator.com and we'll look at the data.
Personally, I thought this was a decently entertaining idea and was a nice break from AI hype and other slightly depressing news.
Also, HN is generally very random - some things succeed and others don't. While I understand the sentiment, imo your message came off a bit abrasive haha.
The price numbers look weirdly specific, I wonder where they came from.
Personally, the thing I'm most excited about is the FrontierCode 2.0 score, which is a benchmark I trust a bit more - 31 seems to be roughly on par with 6.1 Sol and Opus 5.5 medium
I have essentially no knowledge in this field, but another concern may be that if the model has minimal cybersecurity knowledge, it may also implement insecure systems as a side effect.
> LLMs need an insane amount of text. Dessa learned language from hundreds of times fewer words (in fairness, LLMs also have to learn C++ and whatever the hell Angular is).
Now that a larger proportion of text is AI, I'm appreciating human-written text more and more; this got a good chuckle out of me.
I've definitely seen LLMs compose jokes with this structure a lot where "whatever the hell ___ is" is in parenthesis. Not saying this is AI generated tho
I have a “style guide” markdown that is pretty expansive
I run an RLHF style loop with me in the middle for all my writing now where I give a voice rant that is over expressive (aka redundant samples of concepts that I want to express clearly) in order to manage lossy compression steps
Then I will manually clean up that last 5% after a half dozen rounds
That sequence goes into the style guide to be referenced as a reasoning chain of thought to map rant > output
It’s been three years of tuning I’d suspect at this point
I've recently been using gemini argon as a voice judge. so it goes claude ( with style guide) -> voice judge with argon -> claude adjusts. I do that in a few loops before it hard stops if it can't reconcile, and pushes to me for review.
Super interesting read; I especially found this letter from "P791" fascinating:
> Hi, Wonyoung, I map North Korea to help North Koreans.I select areas that look like they might be good points to escape. In particular, the detailed mapping around Phungso-ri (풍서리) is almost entirely my work.I mostly map along the Tumen River, both on the North Korean and Chinese sides. It is important to map the fences, roads, and towns on the Chinese side.
They chose to cross anyway knowing the risks, and it's still preferable to death by firing squad.
"Beyond Utopia" is a harrowing documentary about a South Korean pastor who helps people escape NK, filmed on the trail side by by side with along some actual refugees. It illustrates how complex, dangerous and utterly corrupt the process of getting out is, and also mentions the role of local gangs: they detain refugees and then do a bidding war between the authorities and relatives to extract every penny.
FWIW, my tests used only ranking. I used Kev to drive E2E test runs using agent-device, where Kev had to decide the next action - like pressing a button, or scrolling down etc, to reach a certain goal (UI state). It went surprisingly well, but 4B BF16 was significantly better than 8B Q8. The latter made some wrong decisions in every run while the former was almost at Luna precision.
Fair point! I've actually thought about that before; I've tried to be extremely clear in the project's README with a disclaimer that this is a non-commercial hobby project and is not affiliated with the official Raycast team in any way.
The name is just for identification, as the project's goal is to be a compatible, open-source alternative for the Linux community, a platform they don't currently serve.
That being said, I'll definitely keep it in mind. Thanks for bringing it up!
That shouldn't matter. They might even have a Linux version in the works, given they are doing Windows now. They are within their rights to ask you to get rid of it. You also seem to be using their brand assets like the logo. I get your intention and love what you were able to accomplish but if you intend for this to grow, you are better off doing this now.
True, but a cease & desist will likely include the demand that they cease all operations, and they might be willing to fight that in court, possibly seek damages, etc however likely or unlikely it is that it would hold up. They can pay for a few hours of a lawyer's time to intimidate the OP.
The launcher UI is AppKit while the extension APIs allow third-party developers to write them in TS and a React subset. They have a custom renderer for React that turns that into AppKit primatives. So similar in concept but custom and specific to their usecase.
“Just for identification” is the point — the name Raycast identifies their product, and it’s their trademark. You can’t use it without permission, even with a disclaimer in the readme.
That’s precisely what they’d dislike about it. You’d be creating “brand confusion” by using their trademark in your own name. You couldn’t make “My Cola (Recreating Coke)” without getting an expensive and inconvenient letter from their legal team.
It's also worse than that. It uses the Raycast logo directly in the launcher itself. Which is odd because just above this, OP says:
"I've actually thought about that before; I've tried to be extremely clear in the project's README with a disclaimer that this is a non-commercial hobby project and is not affiliated with the official Raycast team in any way."
Clearly a bright kid, but that's quite a fumble. Among my ideas for being extremely clear about not being affiliated with Raycast I would have to say using their name and using their logo together would be the worst way to communicate that.
I've had to look into for my own side projects, you don't want to include brand names, trademarks, etc in your own projects' names and you should be very wary about how you use them in your marketing if you choose to do so at all.
Personally, I thought this was a decently entertaining idea and was a nice break from AI hype and other slightly depressing news.
Also, HN is generally very random - some things succeed and others don't. While I understand the sentiment, imo your message came off a bit abrasive haha.
[1] https://news.ycombinator.com/newsguidelines.html
reply