I got fooled by AI-for-science hype–here's what it taught me
31 by qianli_cs | 5 comments on Hacker News.
31 by qianli_cs | 5 comments on Hacker News.
The Entropy of Thought: Why Our Minds Gravitate Toward Divided Realities
7 by victorasao | 2 comments on Hacker News.
7 by victorasao | 2 comments on Hacker News.
Finland announces migration of its rail network to international gauge
22 by axelfontaine | 13 comments on Hacker News.
22 by axelfontaine | 13 comments on Hacker News.
Center for AI Safety's new spokesperson suggests „burning down labs"
9 by MrBuddyCasino | 2 comments on Hacker News.
9 by MrBuddyCasino | 2 comments on Hacker News.
The Behavior of LLMs in Hiring Decisions: Systemic Biases in Candidate Selection
13 by hunglee2 | 1 comments on Hacker News.
13 by hunglee2 | 1 comments on Hacker News.
Linguists Find Proof of Sweeping Language Pattern Once Deemed a 'Hoax'
9 by bryanrasmussen | 9 comments on Hacker News.
9 by bryanrasmussen | 9 comments on Hacker News.
Show HN: JavaFactory – IntelliJ plugin to generate Java code
5 by javafactory | 0 comments on Hacker News.
Hi HN, I built a code generator plugin for IntelliJ that uses LLMs to create repetitive Java code like implementations, tests, and fixtures — based on custom natural-language patterns and annotation-based references. Most tools like Copilot or Cursor aim to be general, but fail to produce code that actually fits a project structure or passes tests. So I made something more explicit: define patterns + reference scope, and generate code consistently. In this demo, 400 lines of Java were generated in 20 seconds — and all tests passed: https://www.youtube.com/watch?v=ReBCXKOpW3M GitHub: https://ift.tt/TSc78bX
5 by javafactory | 0 comments on Hacker News.
Hi HN, I built a code generator plugin for IntelliJ that uses LLMs to create repetitive Java code like implementations, tests, and fixtures — based on custom natural-language patterns and annotation-based references. Most tools like Copilot or Cursor aim to be general, but fail to produce code that actually fits a project structure or passes tests. So I made something more explicit: define patterns + reference scope, and generate code consistently. In this demo, 400 lines of Java were generated in 20 seconds — and all tests passed: https://www.youtube.com/watch?v=ReBCXKOpW3M GitHub: https://ift.tt/TSc78bX
Show HN: Text to 3D simulation on a map (does history pretty well)
10 by lukehollis | 5 comments on Hacker News.
Simulate anything on a map from a text prompt -- and conduct risk analysis against LiveUA map's global realtime data points from social media and news sources. I trained a GPT-2-size model on historical incident data used to predict things that will go wrong. As historian Benjamin Breen mentions, the leading language models are good historians, so the application will simulate historical events pretty well also. I include a Multi-Agent RL Urban Mobility model in progress displayed on the map as small white cubes representing traffic and pedestrians. Around SF, it uses real census data and other sources for semantically meaningful day plans, etc. It will populate where you move the map, albeit a little slowly. This is based on previous work on my GitHub--I hope to connect it to Unreal's city samples project soon. The simulations are pretty simple so far but will grow in complexity soon. I won the AGI House World Models Hackathon with this and the MARL model. Many thanks to Shota Matsuda and Garrett Johnson for the cloud and atmospheric effects libraries on Github at takram-design-engineering/three-geospatial Glad for feedback, and thanks for trying it out!
10 by lukehollis | 5 comments on Hacker News.
Simulate anything on a map from a text prompt -- and conduct risk analysis against LiveUA map's global realtime data points from social media and news sources. I trained a GPT-2-size model on historical incident data used to predict things that will go wrong. As historian Benjamin Breen mentions, the leading language models are good historians, so the application will simulate historical events pretty well also. I include a Multi-Agent RL Urban Mobility model in progress displayed on the map as small white cubes representing traffic and pedestrians. Around SF, it uses real census data and other sources for semantically meaningful day plans, etc. It will populate where you move the map, albeit a little slowly. This is based on previous work on my GitHub--I hope to connect it to Unreal's city samples project soon. The simulations are pretty simple so far but will grow in complexity soon. I won the AGI House World Models Hackathon with this and the MARL model. Many thanks to Shota Matsuda and Garrett Johnson for the cloud and atmospheric effects libraries on Github at takram-design-engineering/three-geospatial Glad for feedback, and thanks for trying it out!
CRLF Injection in `–proxy-header` allows extra HTTP headers (CWE-93)
5 by oblivionsage | 2 comments on Hacker News.
5 by oblivionsage | 2 comments on Hacker News.