Hacker Newsnew | past | comments | ask | show | jobs | submit | hcnews's commentslogin

> It is weird how humans are biased like that.

We are able to cleanly separate facts from non-facts (for the most part). This is what LLM are trying to replicate now.


I think the LLM is just trying to be useful, not omniscient. Binary thinkers are probably not going to be able to appreciate the difference, however.

If you want the AI to identify a dog, we are done. If you want the AI to identify subtle differences from reality, then you are going to have to use a different technique.


> What I like about this post is that it highlights something a lot of devs gloss over: the coding part of game development was never really the bottleneck. A solo developer can crank out mechanics pretty quickly, with or without AI.

This is not true at all. I have never worked on games and it will take me quite a while (even months) to write a "basic" game. While I know a lot of good practices about software development and decade+ of FAANG experience, I don't know the intricacies or even the basics of game development.

I recently experienced this for a different usecase. As an experienced backend developer, I wanted to automate some javascript/browser stuff. I tried on my own for 2-3 days and had couple of prototypes but nothing actually worked. I spent 2 hours with an AI and I had a working solution. We even iterated together quickly and solved some runtime issues and the solution is working for me seamlessly now.

So, I definitely see value of AI even for coding for experienced developers like myself.


> have never worked on games and it will take me quite a while (even months) to write a "basic" game.

You're contradicting yourself. I promise it wouldn't take you months, unless you're just a really bad developer.


What is the contradiction? I am guessing it will take me a non-significant effort to learn game mechanics and code them etc.


You've never worked on games yet you are exceedingly confident about your estimation or the difficulty involved.

It's not that difficult to get a base level game up and running; ESPECIALLY with modern tooling.


Don't be a prick in public man, it looks bad


I mean it's a simple fact that the baseline for creating a game, roughly using the average developer experience/capability, is not months. Making a _good_ game might take months, it often takes years.

And that's the part AI is not going to be able to help you with.


Making a good boardgame, with zero need for programming, excluding artwork, is months or years of work. I would expect that much at a minimum for a (good) simple digital game, unless it is just going to sell on graphics and marketing alone (or luck).


Maybe you are a games developer and are overlooking the fact that people have to first learn the basic apis/models/etc. of graphical systems, engines, etc. before using them. Not sure how you are saying that it wouldn't take a few weeks to code even a simple production game like chess or more complicated but still simple Jump king etc.

Just think of the speciality in which you aren't an expert, javascript/storage/networking ...


I've dabbled and continue to dabble in areas where I know nothing about. And in this case, there's nothing super special about making a game.


> Almost nobody sets prices manually. You either use Airbnb's pricing algorithm, or one from a third party. Either way it's set automatically based on local occupancy rates/hotel prices/etc.

This seems pretty undesirable. Very easy for Airbnb/third party to increase prices even without demand just to increase their prices.

We recently saw a similar price fixing lawsuit for renters. Landlords, co-ordinating together, ended up increasing prices of Condos across major American cities (via means of a third party). The consumer ends up paying unnecessarily high prices in an inelastic market.


Could you anonymize and share your last 5-10 prompts? Just wanna understand how people are using Claude Code.


These aren't that fun but sure.

- https://gist.github.com/backnotprop/ca49f356bdd2ab7bb7a366ef...

- https://gist.github.com/backnotprop/d9f1d9f9b4379d6551ba967c...

- https://gist.github.com/backnotprop/e74b5b0f714e0429750ef6b0...

- https://gist.github.com/backnotprop/91f1a08d9c27698310d63e06...

- https://gist.github.com/backnotprop/7f7cb63aceb7560e51c02a9d...

- https://gist.github.com/backnotprop/94080dde34bfca3dd9c48f14...

- https://gist.github.com/backnotprop/ea3a5c3a31799236115abc76...

Taken from 2 recent systems. 90% of my interaction is assurance, debugging, and then having claude operate within the meta context management framework. We work hard to set the path for actual coding - thus code output (even complex or highly integrated) usually ends up being fairly smooth+fast.

When I "wake" CC up I usually use a prompt like this to preface any complex work: https://gist.github.com/backnotprop/d2e4547fc4546eea071b9b68... (the goal is to get all relevant context in-memory).

For most planning I use Gemini. I copy either the entire codebase (if less than ~200k tokens) or select only that parts that matter for the task in large codebases. I built a tool to help me build these prompts, keep the codebase organized well in xml structure. https://github.com/backnotprop/prompt-tower


worth noting that some of the prompts are related to the project context management system i use: (obfuscated business details) https://gist.github.com/backnotprop/4a07a7e8fdd76cbe054761b9...


Interesting. Thanks.

Could you explain why there is no punctuation?


Ah yea sorry that is an export error... I copied prompts directly out of Claude Code and when I do that it copies all of the ascii/tui parts that wrap the message... I used some random "strip special chars" site to remove those and was lazy about adding actual punctuation back in.


"Ensure all our crons publish to telegraf when they start and finish. Include the cron name and tenant id when applicable. For crons that query batch jobs, only publish and take a lock when there is work to do. look at <snip> as an example. Here is the complete list to migrate. Create a todo list and continue until done. <insert list of 40 file paths>"

(updated for better example)


The thing I forgot is the command for it to get the next set of files to process. Otherwise it will migrate 30% of them and say "look dad, I'm done!"


I used it yesterday to convert a website from tailwind v1 to v4. Gave it the files (html/scss/js), links to tailwind and it did the job. Needed some back and forth and some manual stuff but overall it was painless.

It is not a challenging technical thing to do. I could have sat there for hours reading the conversion from v1 to v2 to v3 to v4. It is mostly just changing class names. But these changes are hard to do with %s/x/x, so you need to do them manually. One by One. For hundreds of classes. I could have as easily shot myself in the head.

> Could you anonymize and share your last 5-10 prompts?

The prompt was a simple "convert this site from tailwind v1 to v4". I use neovim copilot chat to inject context and load URLs. I have found that prompts have no value, it is either something the LLM can do or not.


lol hyperbole much.


What’s the hyperbole? This is partly a recruiting tool. If you think the game is not exciting then this is probably not the career for you. Do you have something more substantive than a weak attack?


I have been texting from my laptop from 2010 via Google Voice.


What are the property crimes in SF/Bay Area? Just curious.


The big ones are car break-ins and bike thefts.


For a lot of these changes, you need a motivated and engaged enforcer/system-owner who will work through these challenges. It takes time and effort to change the culture of a group. I can't imagine someone wanting to change unless they either gain a strong motivation (highly unlikely given that they have been in the current condition for a while themselves) or they are given the right framework/setup by someone else (govt. in this case). So, this is a hard problem and one shouldn't get disheartened due to no progress so far.


Maybe you were technically right for some small scope of the problem, no proper industry definition of GC was supported by C++ by any of the major compiler. So, the HPC scientists were right imo.

Being technically right for an aspect that doesn't matter is a common trope that a lot of software engineers fall for.


Would be interested in a link to a model if you have one handy!


That could be any gaming laptop from any manufacturer., those are the only ones who still ship with upgradable RAM and dual M.2 slots.


Finding one with a decent screen for anything other than gaming is the trick. I linked it up there, but this is IPS with 100% sRGB, more brightness than most people need, 16:10 (vertical space is nice!), 165Hz, and matte! Most gaming laptops are...not that. Maybe 50% sRGB on a dim glossy TN screen.


>Most gaming laptops are...not that.

Then you haven't been looking close enough. Cheapo gaming laptops yes, but Lenovo Legion, Asus G14 plus most other more premium models from other manufacturers have very good screens.


Lenovo Thinkpads? You can absolutely have two m2 slots with a good screen and a solid graphics card. https://psref.lenovo.com/Product/ThinkPad/ThinkPad_P1_Gen_6


I think any midrange gaming laptop in 2023 has that plus much better response times compared to apple laptops


Workstation laptops from Lenovo and Dell have upgradeable RAM and have been offering 128 GB RAM for something like 6 years.


https://www.bhphotovideo.com/c/product/1746503-REG/lenovo_82...

B&H doesn't stock it anymore, but it looks like other places still sell it with updated specs.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: