HackerTrans
TopNewTrendsCommentsPastAskShowJobs

emurph55

no profile record

Submissions

Show HN: Snapalabra - AI Assisted Language Learning and Practice

app.snapalabra.com
2 points·by emurph55·6 เดือนที่ผ่านมา·0 comments

Show HN: Review code as it is written

npmjs.com
2 points·by emurph55·8 เดือนที่ผ่านมา·2 comments

Show HN: On-the-Fly Code Review

github.com
1 points·by emurph55·8 เดือนที่ผ่านมา·0 comments

Show HN: Ollama-watcher – On the fly code reviews using Ollama

npmjs.com
2 points·by emurph55·8 เดือนที่ผ่านมา·0 comments

Show HN: A Vim plugin for displaying information on NPM packages

github.com
3 points·by emurph55·ปีที่แล้ว·0 comments

Show HN: Generate Geocities style pages on any subject

thedeadweb.eu
2 points·by emurph55·ปีที่แล้ว·1 comments

Show HN: TheDeadWeb.eu – Explore an AI generated web

thedeadweb.eu
1 points·by emurph55·ปีที่แล้ว·1 comments

Show HN: The Dead Web

thedeadweb.eu
2 points·by emurph55·ปีที่แล้ว·0 comments

Show HN: Free Pilot – AI Autocomplete plugin for Vim

github.com
4 points·by emurph55·ปีที่แล้ว·0 comments

Show HN: Detective Stories -Lateral thinking detective game with Deepseek player

detective-stories.com
13 points·by emurph55·ปีที่แล้ว·7 comments

comments

emurph55
·8 เดือนที่ผ่านมา·discuss
yeah, I am not really convinced of any real practical use myself tbh. I just wanted to try it out!
emurph55
·ปีที่แล้ว·discuss
Really enjoy this method. Please add Irish if you can! TG4 could be used as possible source material: https://www.youtube.com/@TG4TV/videos
emurph55
·ปีที่แล้ว·discuss
yeah, it usually functions like a simplified wikipedia. It is more useful for simpler subjects in its current form, but ultimately its just a bit of fun
emurph55
·ปีที่แล้ว·discuss
On a slightly related note, I have created a tool for generating web pages based on any subject using different "themes". You can create one here with a "Mario-Bro's" theme for example: https://thedeadweb.eu/?q=honey&style=mario-bros
emurph55
·ปีที่แล้ว·discuss
Some quick examples of some different themes: Subject: Large Hadron Collider:

Minimalism: https://thedeadweb.eu/?q=large%20hadron%20collider&style=pur...

Mario-bros: https://thedeadweb.eu/?q=large%20hadron%20collider&style=mar...

Vim: https://thedeadweb.eu/?q=the%20large%20hadron%20collider&sty...

Andy Warhol: https://thedeadweb.eu/?q=the%20large%20hadron%20collider&sty...
emurph55
·ปีที่แล้ว·discuss
Any stories that have been written by AI are marked as such (they are categorized as user submission stories where the author is credited as the AI model). Interestingly the lowest ranked story on the site is one of those, although that was created with an older model. I had never thought of the site as being an "AI product" personally. I just wanted an excuse to play around with web sockets initially, but if I can improve the AI player maybe it will eventually go more in that direction.
emurph55
·ปีที่แล้ว·discuss
that's pretty funny. Yeah, its far from perfect in terms of implementation at the moment. I was more curious to see if it was capable of understanding the game more than anything for the moment. Previous attempts with other models had proved to be disappointing. I will tweak the prompts to resolve that issue soon enough though. Like you say, it should be bread and butter for this.
emurph55
·ปีที่แล้ว·discuss
I have had this lateral thinking game online for a while. The jist of the game is that one player asks a "host" a series of questions in order to reach a full understanding of what happened in a story, based on an initial premise.

I have tried in the past at adding AI players but could never get reliable answers. However, as AI has improved, I decided to give it another go. At the moment it is connected to deepseek v3 with some basic prompts, and it looks to handle the task pretty well. Not yet perfect but it definitely does form an impressive understanding of the stories, and the game itself.
emurph55
·2 ปีที่แล้ว·discuss
I've tried using older models to create a cpu player on this lateral thinking game (https://detective-stories.com) and they were surprisingly bad at giving answers. I am curious to see how well the more recent models will do.