HNHacker News
TopNewBestAskShowJobs

thrwthsnw

52 karma · joined December 9, 2024

submissionscomments
thrwthsnw··on Generative AI runs on gambling addiction – just one more prompt, bro
This is a severely out of touch take.
thrwthsnw··on A deep dive into self-improving AI and the Darwin-Gödel Machine
What is this? Genetics for ants?
thrwthsnw··on Claude Code Is My Computer
Try reading a manuscript copy of a book before it’s been edited. Yes I know some people do this out of interest but for most people it’s not the type of writing they are interested in reading or would get the most out of.
thrwthsnw··on The rise of judgement over technical skill
Just move up an abstraction level and put that flow into planning the features and decomposing them into well defined tasks that can be assigned to agents. Could also write really polished example code to communicate the style and architectural patterns and add full test coverage for it.

I do notice the same lack of flow when using an agent since you have to wait for it to finish but as others have suggested if you set up a few worktrees and have a really good implementation plan you can use that time to get another agent started or review the code of a separate run and that might lend itself to a type of flow where you’re keeping the whole design of the project in your head and rapidly iterating on it.

thrwthsnw··on Isaac Asimov describes how AI will liberate humans and their creativity (1992)
Why do we give awards to Directors then?
thrwthsnw··on Claude can now search the web
every token contributes to the output
thrwthsnw··on With AI you need to think bigger
For category #2 it’s very useful as well and ties in with the theme of the article in that it reduces the activation energy required to almost zero. I’ve been using AI relentlessly to pursue all kinds of ideas that I would otherwise simply write down and file for later. When they involve some technology or theory I know little about I can get to a working demo in less than an hour and once I have that in hand I begin exploring the concepts I’m unfamiliar with by simply asking about them: what is this part of the code doing? Why is this needed? What other options are there? What are some existing projects that do something similar? What is the theory behind this? And then also making modifications or asking for changes or features. It allows for much wider and faster exploration and let’s you build things from scratch instead of reaching for another library so you end up learning how things work at a lower level. The code does get messy but AI is also a great tool for refactoring and debugging, you just have to adjust to the faster pace of development and remember to take more frequent pauses to clean up or rebuild from a better starting point and understanding of the problem.
thrwthsnw··on A Year of Telepathy
Listen to an interview with Noland to find out why. Unfortunately the patient with ALS can’t give an interview because he can no longer speak.
thrwthsnw··on Why the WHO has recommended switching to a healthier salt alternative
Probably because you’ll die if you eat too much.
thrwthsnw··on Why the WHO has recommended switching to a healthier salt alternative
This is absurd, too much potassium is much more dangerous than too much salt.
thrwthsnw··on GitHub reveals how software engineers are purging federal databases
It’s kind of lame that these guys are blacklisting words based on some master list. Normally these things get grandfathered in but I guess they’re just blindly following orders after getting sold down the river. It seems like an insane waste of manpower if you ask me. I’d hate to be the low man on the totem pole slaving away at this kind of bitchwork and getting ragged on by the bossman if I missed a word.
thrwthsnw··on LLMs: Harmful to Technical Innovation?
Good documentation and examples help both the community and LLMs. My suggestion to any aspiring language or framework developers is to spend time creating both. If you really want to turbocharge adoption you could create a tool that automatically translates code examples from popular languages into your own language (and tests that they work) and then publish them online with some helpful comments.
thrwthsnw··on OpenAI O3-Mini
Who determines who gets access to what information? The OpenAI board? Sam? What qualifies as dangerous information? Maybe it’s dangerous to allow the model to answer questions about a person. What happens when limiting information becomes a service you can sell? For the right price anything can become too dangerous for the average person to know about.
thrwthsnw··on Starship Flight 7
The history of rocketry goes much further back than the space shuttle. The shuttle was supposed to be a step towards reusability but didn’t succeed or progress the way they thought it would. Starship is continuing that dream of full reusability and their approach is working. You can’t plan everything on paper when it comes to hardware especially when attempting things that have never been done before, you just don’t have the data in that case. You have to build prototypes and test them to destruction. All manufacturers do this.
thrwthsnw··on TikTok preparing for U.S. shut-off on Sunday
Is this supposed to be good?
thrwthsnw··on Casual Viewing – Why Netflix looks like that
If people aren’t watching the show why not just make it a radio play?
thrwthsnw··on Casual Viewing – Why Netflix looks like that
We should just get rid of the ratings. They’re a stupid system that hasn’t worked anyways.
thrwthsnw··on Casual Viewing – Why Netflix looks like that
The shorter article is better.
thrwthsnw··on Ask HN: Predictions for 2025?
Wouldn’t solve anything, social media would just fragment even more. People will move to unregulated sites. Full on dictatorships can’t even prevent people from using the internet so how does anyone think this would work?
thrwthsnw··on Infinigen: Infinite Photorealistic Worlds Using Procedural Generation
He’s asking if anyone is training using data created from a system like this, not if this uses AI.
thrwthsnw··on GPT-5 is behind schedule
Seriously? All they do is produce a “confidence metric”
thrwthsnw··on GPT-5 is behind schedule
Which Americans, North or South?
thrwthsnw··on GPT-5 is behind schedule
Everything you said is parroting data you’ve trained on, two thirds of it is actual copy paste
thrwthsnw··on GPT-5 is behind schedule
Private data is 90% garbage too
thrwthsnw··on GPT-5 is behind schedule
The thing that is killing us is the same thing that is killing capitalism
thrwthsnw··on Boardgame.io: an engine for creating turn-based games using JavaScript
Go to the projects page on the docs site
thrwthsnw··on Computing Inside an AI
This is the wrong direction, it is retrograde trying to shoehorn NATURAL LANGUAGE UNDERSTANDING into existing GUI metaphors.

Instead of showing a “discoverable” palette of buttons and widgets which is limited by screen space just ASK the model what it can do and make sure it can answer. People obviously don’t know to do that yet so a simple on screen prompt to the user will be necessary.

Yes we should have access to “sliders” and other controls for fine tuning the output or maintaining a desired setting throughout generations but those are secondary to the ability of the models to make sweeping and cohesive changes and provide many alternatives for the user to CHOOSE from before they get to the stage of making fine grained adjustments.

thrwthsnw··on Assisted dying now accounts for one in 20 Canada deaths
God loves you.
thrwthsnw··on What we know about the mysterious drones flying over New Jersey
Gas mileage, safety, noise, cost, on top of the fact they already have tons of long range single prop drones kitted out with surveillance gear. Almost all of the videos look like predator style drones flying search grids. Maybe they have some large quadcopter drones in the air but I haven’t seen a single photo or video of anything that looks like one.
thrwthsnw··on Sora is here
There are private citizens that own and operate all of those things.