2
points
anonfunction
Joined 1,995 karma
https://github.com/montanaflynn
[ my public key: https://keybase.io/anonfunction; my proof: https://keybase.io/anonfunction/sigs/XDrAMXPVLlybrKb6hXdzMdcWgkFdp5pCjq-yb8FBuZo ]
- anonfunction parentThe console / login pages are showing an error still.
- Seems like you're experiencing the hacker news hug of death.
- So the announcement said the API works with the new model, so I updated my Golang SDK grail (https://github.com/montanaflynn/grail) to use but it returns a 500 server error when you try to use it, and if you change to a completely unknown model it's not listed in the available models:
POST "https://api.openai.com/v1/responses": 500 Internal Server Error { "message": "An error occurred while processing your request. You can retry your request, or contact us through our help center at help.openai.com if the error persists. Please include the request ID req_******************* in your message.", "type": "server_error", "param": null, "code": "server_error" } POST "https://api.openai.com/v1/responses": 400 Bad Request { "message": "Invalid value: 'blah'. Supported values are: 'gpt-image-1' and 'gpt-image-1-mini'.", "type": "invalid_request_error", "param": "tools[0].model", "code": "invalid_value" } - Yeah I just tried it and got a 500 server error with no details as to why:
Interestingly if you change to request the model foobar you get an error showing this:POST "https://api.openai.com/v1/responses": 500 Internal Server Error { "message": "An error occurred while processing your request. You can retry your request, or contact us through our help center at help.openai.com if the error persists. Please include the request ID req_******************* in your message.", "type": "server_error", "param": null, "code": "server_error" }POST "https://api.openai.com/v1/responses": 400 Bad Request { "message": "Invalid value: 'blah'. Supported values are: 'gpt-image-1' and 'gpt-image-1-mini'.", "type": "invalid_request_error", "param": "tools[0].model", "code": "invalid_value" } - I made this app to scratch an itch of mine caused by flakey ethernet connection through my dock. Fairly often my internet connection falls back to wifi instead of ethernet though my dock. There's no built-in menu bar icon I could find to show ethernet connection status and opening the network pane in system settings was tiresome. So I decided to make my first mac app!
Claude code wrote all the code, openai generated the app icon. I wrote a small golang program to take the 1024x1024 png from openai and resize/rename it to the expected iconset format and json file.
This was a fun experiment, I don't think there's ever been a time where people could so easily create native applications!
- Thank you, this has been fixed!
- Wow I had not known of that! This is mostly just a quick tool I wanted but something to think about if anything further were to come from it.
- There is an example linked to on the homepage of this submission but here it is:
- Possibly. I had to kind of be very specific to get the model to link to the pages in a specific format my frontend can parse and then interact with the pdf viewer[1]. It seems very full featured so it may have a way to highlight portions of the page, but my experience with PDFs leads me to believe it would be tricky.
- That seems like a social network? This is just a tool to have an AI model answer questions without needing to do anything other than replace the domain.
- I've had better results running it with the Gemini 2.5 Pro model but it's much more expensive. The website is using the very cheap 2.5 flash lite model.
You can run it yourself using the better model to see if you get better results as well:
- Very cool! I chose gemini for two reasons; the first being it supported pdf input and the second the flash lite model being very cheap so I could comfortably make it public and free.
- Thank you, that's probably correct. I think the gemini api might turn the pages into images and use those. Sending the original tex source was something I thought of but not all papers have those submitted.
As for markdown / latex output that could be done, especially for equations! I'll have to look into the best way to render that.
- I hadn't, but at a glance it seems more of a community that an AI tool?
- Thank you! If you have any suggestions feel free to let me know.
- I built it because it was tiresome to save the pdf, open a new window, add it and give a prompt.
Simply replacing the domain arxiv.org with asxiv.org does all that for me now.
Also it links to pages in it's answers and scrolls the pdf to it on click, allowing to view the pdf side by side with the chat.
- Shameless plug but I made a similar tool called asXiv[1] which allows you to "ask" arXiv.org papers questions.
It also recommends questions on initial load that can help understand or explore the paper, here's a demo[2] from the popular Attention Is All You Need paper.
The code is all opensource[3], it uses the google 2.5 flash lite model to keep costs down (it's completely free atm), but that can be changed via env var if you run it locally.
- 161 points
- Any chance you could open source it so we can add more languages and run it locally?
- Continental US (United States) refers to the 48 United States excluding Alaska and Hawaii.
- 63 points
- What's TAO?
- This is not Kemal Kilicdaroglu who is the main challenger to Erdoğan, and in fact could help his chances.
1. https://www.reuters.com/world/middle-east/turkeys-erdogan-la...
- Watching on the Apple TV+ app on an Android TV it frequently replays the same episode I already watched or starts at some random time earlier in the episode than when I left off which is a pain to fix using their scrubbing feature which is itself a bad experience.
- 2 points
- Thank you this is actually something that appears to solve one of my main issues. I did not see this before, and it's not linked to from their dashboard UI or the ethereum gateway docs [1]. It appears that I could make the DNS record go through another cloudflare product Cloudflare Zero Trust[2] which can do the access management.
While this is good to know, I still would much like visibility into public usage and user set billing limit caps. A large portion of use cases for an ethereum gateway is going to be frontend client side calls, and yes I know I could make another proxy layer on my own servers and set limits there, which if I could do things over I would have.
1. https://developers.cloudflare.com/web3/ethereum-gateway/ 2. https://developers.cloudflare.com/cloudflare-one/
- Actually I had a similar experience with trying to create a business account, only the account who created it can set up billing. There is no concept of a team account or billing managers which surprised me.