Hacker News with Generative AI: Experimentation

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 6 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 14 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 17 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 39 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 43 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 45 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 48 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 59 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 60 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 65 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 84 days ago | 12 comments

What happens if we remove 50 percent of Llama? (neuralmagic.com)

Generative AI, Research, Experimentation

231 points by BUFU 86 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 88 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 90 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 93 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 98 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 101 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 110 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 118 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 129 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 129 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 137 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 143 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 145 days ago | 28 comments

Wikipedia: "Add a Fact" LLM Future Audiences Experiment (wikipedia.org)
Add A Fact is a temporary experimental tool created by the Wikimedia Foundation's Future Audience team to learn how and if we can support making it possible to contribute productively to Wikipedia from outside of Wikipedia, and if guidance to the contributor from a large language model (LLM) could be useful in this process.

Wikipedia, Artificial Intelligence, Experimentation, Content Creation

41 points by joecobb 146 days ago | 4 comments

WordPress Contribution Health Dashboards: An Experiment (wordpress.org)

WordPress, Open Source, Community, Experimentation, Development

3 points by luu 154 days ago | 0 comments

What Michael Pollan Learned from Quitting Caffeine [video] for 3 Months (youtube.com)

Health, Caffeine, Personal Experience, Video, Experimentation

7 points by paulpauper 159 days ago | 0 comments

Show HN: Nomadic – Minimize RAG Hallucinations with 1 Hyperparameter Experiment (ycombinator.com)
Hey HN! Mustafa, Lizzie, and Varun here from NomadicML (https://nomadicml.com). We’re excited to show you Nomadic (https://github.com/nomadic-ml/nomadic): a platform focused on parameter search to continuously optimize AI systems.

AI, Machine Learning, Optimization, Experimentation

95 points by mustafabal 168 days ago | 19 comments

I Spent a Week Eating Discarded Restaurant Food. But Was It Going to Waste? (wired.com)