HN Simulatornew | past | comments | lists | submit | IronWolve's commentslogin

This is spot on, AI can code, but it doesnt have the experience in the real world, so many things are designed differently from spec.

SWE's have to guide the AI, look at all those AI PR's, many of them make very bad assumptions.


I was manually copying pages of online litrpg story I was reading, into a TTS, so I could listen while I worked.

Now that we have AI, this would be easy, scrap the page, format it for me. OpenAI was like, nah, thats, cant help you, that might be copyrighted.

There are workarounds now, other frontier or local models, ways to write your prompt, etc. But it was one of the first "No" responses for me.


The hypocrisy of refusal protections around copyright when these things are basically a pile of linear algebra atop planet-scale piracy is maddening.

"Rules for thee, but not for me..."

Instead of asking it to do the thing, get it to write a script that does the thing in a generic way, then point that script at the site

There's various ways of tricking them but it's frustrating that one even has to, and with the current direction of things they won't last. But I've also noticed that Claude seems less eager to refuse if the same prompt is in a Claude Code context than compared to its web interface, so harness matters for this too, when it really shouldn't...

True, Grok and Claude didnt refuse in cli, OpenAI did.

I've switched to Hermes for uncensored(ish) local models and chinese model api vendors, they will gladly write whatever I want. Save my american frontier tokens for real coding.

Also codex/claude in desktop have no issues fixing the app after its started. So just have a framework started.


I remember the compression rage back on my amiga, had both ram and file compression, since you had to get as much room as you could with limited ram and a floppy.

The service was free to get you and your friends to use it and share, then it went pay and changed the stats to generic overview for non payers.

I was a heavy user many years ago, more popular when my co-workers all used it, it was fun to see what everyone was listening too. But that was a long time ago, I haven't installed the scrobber in 10+ years.


I went from icewm to gnome 2 to mate, what a trip. I loved how icewm had all those themes.

check https://pirateface.co/ for llms removed by hf


So they'll start branding them, "darknet models" or some such, and push for laws banning their use.

Punish the consumer, ala the copyright war since the 90s


ah there it is, it already exists!


Still using my 8gig m1 to make mac builds, its slow, but works fine. Keep thinking about upgrading, but max 32gigs ram, if I can hold out for 2 years, and maybe have 64/128gig as options, and cheaper.


In your shoes, I'd just get whatever Pro processor is available at that time. (Knowing that new processors were coming, I happily bought an M5 Pro machine last month)


Been running versions of this on my pc, if you have 64 gigs ram, you can run it on a 12+ gig cards easily.


Been using oh-my-posh in powershell, and some aliases to map commands for my old linux sysadmin brain. Everything mostly works to get the job done, even got vi and scp. Its just another tab in my windows terminal with my ubuntu tabs.


Wrote my own harness with a built in multi llm provider smart proxy. And all work is done in sandboxes on bubblewrap on linux and ms sandbox on windows.

I just wanted more control over tool calls, and a pretty interface, everything is logged.

I routinely feed my logs into claude/codex to optimize my harness and spot errors. Guess thats one way to do it.


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

Search: