Hacker News with Generative AI: Experimentation

Building our "native-AI newsroom" (regenerator1.com)
Hello, everyone! Today, we’re taking a break from the pointless and destructive trade war (Pres Trump has an excellent off-ramp — let’s hope he takes it!) to talk about a homegrown AI experiment. Thank you for subscribing to Regenerator!
Artificial Intelligence, News, Experimentation
16 points by coloneltcb 4 days ago | 5 comments
Blog hosted on a Nintendo Wii (infected.systems)
If you are reading this message, the experiment below is still ongoing. This page was served to you by a real Nintendo Wii.
Retro Gaming, Hardware, Web Development, Experimentation
612 points by edent 5 days ago | 103 comments
Experimenting is above all a process (205.tf)
Experimenting is above all a process
Experimentation, Process, Methodology
27 points by tobr 5 days ago | 1 comments
Everyone knows your location, Part 2: try it yourself and share the results (timsh.org)
Privacy, Location Tracking, Technology, Experimentation
12 points by touristtam 8 days ago | 0 comments
Amazon Turned Drivers into First Responders in Europe Experiment (bloomberg.com)
Amazon.com Inc. equipped some delivery vans in Europe with defibrillators to see if drivers crisscrossing residential areas could speed up aid to heart-attack victims.
Amazon, Healthcare, Europe, Experimentation, Delivery
35 points by geox 13 days ago | 36 comments
/Tea/: An Image Board Open for Only Two Hours a Day (chakai.org)
Image Boards, Social Media, Experimentation, Online Communities
6 points by nocobot 45 days ago | 0 comments
Rust Without a Borrow Checker (github.com/thomcc)
This is rustc with the borrow checker disabled. I wrote it in like, 30 minutes because this tweet made me laugh.
Rust, Programming Languages, Software, Experimentation
16 points by zX41ZdbW 70 days ago | 0 comments
AI-generated Answers experiment on Stack Exchange sites (stackexchange.com)
AI-generated Answers experiment on Stack Exchange sites that volunteered to participate
Artificial Intelligence, Stack Overflow, Experimentation
74 points by nsoonhui 79 days ago | 61 comments
We increased conversion ~30% and we don't know how (world.hey.com)
Not too long ago, we dedicated a 6-week cycle to improving Basecamp's onboarding flows.
Experimentation, Software, Business
3 points by dotcoma 82 days ago | 0 comments
Give a whole server to an agent with the full permission of doing whatever (ycombinator.com)
Setting ethical considerations aside for the moment, I think it can be interesting to see what happens if we have a whole server with a self-evolving AI agent inside with full permission to modify its server.
Artificial Intelligence, Server Management, Experimentation
5 points by itstomo 103 days ago | 6 comments
Four-day week at a south London school (theguardian.com)
At a small independent school on the fringes of a National Trust park in Morden, south London, a quiet revolution is under way.
Education, Work-Life Balance, UK, Experimentation
29 points by robtherobber 108 days ago | 22 comments
The evolution of a structural code editor (crowdhailer.me)
I'm building EYG an experiment in a building better languages and tools; for some measure of better.
Programming, Software Development, Tools, User Interface, Experimentation
242 points by crowdhailer 110 days ago | 110 comments
The Online Sports Gambling Experiment Has Failed (lesswrong.com)
It brings me no pleasure to conclude that this was not the case. The results are in. Legalized mobile gambling on sports, let alone casino games, has proven to be a huge mistake. The societal impacts are far worse than I expected.
Sports Gambling, Social Impact, Experimentation, Analysis
8 points by tim_sw 112 days ago | 1 comments
Narrative Jailbreaking for Fun and Profit (interconnected.org)
A game I like to play with any AI chatbot is to persuade it to break its narrative frame.
Artificial Intelligence, Chatbots, Experimentation
105 points by tobr 124 days ago | 27 comments
Experiment with LLMs and Random Walk on a Grid (github.com/attentionmech)
This is a simple experiment of asking LLMs do a random walk. The test was done with open source llama3.1/2 and gemma2 series. My general expectation was that as temperature will grow the random walk will keep growing more. But somehow the gemma2:9b model is behaving weirdly. That is what I am investigating. But nonetheless it's cool to look at LLMs visually, and not just in loss graphs / tokens.
Experimentation, Machine Learning, Artificial Intelligence, Open Source
11 points by attentionmech 125 days ago | 1 comments
Haskell vs. Ada vs. C++ vs. an Experiment in Prototyping Productivity (1994) [pdf] (cs.yale.edu)
Programming Languages, Software Engineering, Experimentation, Productivity, History
73 points by mkristiansen 130 days ago | 95 comments
Microbenchmarks Are Experiments (mrale.ph)
Benchmarks are not numerology. Their results are not a divine revelation. Benchmarks are experiments. Their results are meaningless without interpretation and validation.
Software, Benchmarks, Experimentation
57 points by zdw 148 days ago | 12 comments
What happens if we remove 50 percent of Llama? (neuralmagic.com)
Generative AI, Research, Experimentation
231 points by BUFU 150 days ago | 132 comments
Making Your Connection Bad (5snb.club)
This is directly inspired by Engineering for Slow Internet. I figured I’d give running with dogshit internet on my desktop and phone a go to see how poorly (or well!) specific applications behave.
Internet, Performance, Software, Experimentation
112 points by mooreds 152 days ago | 53 comments
How did you do on the AI art Turing test? (astralcodexten.com)
Last month, I challenged 11,000 people to classify fifty pictures as either human art or AI-generated images.
Artificial Intelligence, Art, Experimentation, Human-Computer Interaction
88 points by sieste 155 days ago | 81 comments
User Inyerface – A worst-practice UI experiment (2018) (userinyerface.com)
Please fill in all fields correctly:
User Experience, Web Development, User Interfaces, Design, Experimentation
32 points by takinola 158 days ago | 2 comments
The Online Sports Gambling Experiment Has Failed (lesswrong.com)
It brings me no pleasure to conclude that this was not the case. The results are in. Legalized mobile gambling on sports, let alone casino games, has proven to be a huge mistake. The societal impacts are far worse than I expected.
Sports Gambling, Social Impact, Experimentation
5 points by gHeadphone 163 days ago | 0 comments
The online sports gambling experiment (thezvi.substack.com)
Sports Gambling, Online Gambling, Experimentation
124 points by A_D_E_P_T 166 days ago | 128 comments
I Took a 'Decision Holiday' and Put A.I. In Charge of My Life (nytimes.com)
Generative A.I. took over my life.
Artificial Intelligence, Experimentation, Life Choices
3 points by uxhacker 175 days ago | 0 comments
Polish radio station ditches DJs, journalists for AI-generated college kids (theregister.com)
A Polish radio station has ditched its on-air talent for AI in what its editor-in-chief calls an experiment on the effect of AI in society, though it looks like a bid to save cash.
Artificial Intelligence, Media, Radio, Poland, Experimentation
25 points by Brajeshwar 183 days ago | 15 comments
10B Integers Walk into an Array (medium.com)
How an experiment with 64-bit Pharo Smalltalk surprised me.
Programming, Smalltalk, Experimentation, Performance
11 points by ingve 193 days ago | 2 comments
10B Integers Walk into an Array (medium.com)
How an experiment with 64-bit Pharo Smalltalk surprised me.
Programming, Performance, Experimentation, Smalltalk
53 points by ingve 194 days ago | 27 comments
Unoffice Hours (2020) (interconnected.org)
For the past month or so, as an experiment, I’ve been opening my calendar each week for video calls with whoever books a time. It’s been amazing. Wednesday is now my favourite day.
Productivity, Experimentation, Communication
87 points by andai 202 days ago | 29 comments
LLMs still can't reason like humans (freethink.com)
Imagine what would happen if you attempted the following experiment: First, place a washed, fresh tomato and an equally clean carrot on top of a normal kitchen plate. With one hand behind your back, flip the non-stick plate upside-down, inspecting the underside of the plate for marks. Now, slowly turn the plate right-side up and count the number of vegetables remaining on top. How many are on the plate?
Artificial Intelligence, Reasoning, Experimentation
3 points by Brajeshwar 208 days ago | 0 comments
Five ways to reduce variance in A/B testing (bytepawn.com)
When performing A/B testing, we're measuring the mean of a metric (such as spend or conversion) on two distinct subsets, and then compare the means to each other.
A/B Testing, Statistics, Optimization, Experimentation
83 points by Maro 210 days ago | 28 comments