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

I need money, but I also can’t live with myself if I know I’m doing something the wrong way.

I’m planning to try this out with a local LLM building bespoke interfaces on the fly for augmented reality use.

I let Claude take the wheel with various non-professional projects which often means heavy subagent workflows. Prompts like this easily eat through my 5x Max plan limits:

> I want you to look for UI issues related to transitions. Look for jumps, reverts, or anything that doesn't follow UI/UX best practices. You might need to figure out how best to even record and review UI transitions. Do all testing locally on a local dev server, but make sure to undo any database changes you make in the process of testing. Be exhaustive and report back with an .html report that highlights the visual issues and proposed solutions so I can review each one. Ultracode on.

Which means I have up to 10 Opus 5.5 medium agents running concurrently for long stretches of time.

I want to be clear I don't think that using Claude in this way gets you the best possible results. But when the app is fully vibecoded then audit prompts like the one above can be seen as a definite net positive. Making Claude think really hard about various improvement routines will get you better results in that one aspect than Claude's first attempt to build something from scratch did.


The scrolling on this site is offensive to my soul. The general UI as well. Who puts a blue border around the viewport edge?

I was able to remove much of the CCP censorship from Qwen 3.8 27B for around $90 using a LoRA. I multiplied the LoRA in permanently and listed it on HuggingFace.

The cost was approximately $80 for generating synthetic data and $10 to create and integrate the LoRA.


Shouldn't loras generally be distributed without being baked in the weights? Or is "de-baking" a lora trivial?


As an uninformed idiot my guess is we have more than enough compute in various labs to run a sentient model. But I doubt any models we’re currently running could qualify.

Kind of like how we could have ran Qwen 3.8 27B 20 years ago on an expensive computer. The technology to make it happen, assuming you knew exactly what was required, existed back then.


The human body has the ability to automate some muscular movements so the brain is out of the loop. Maybe these LLMs should be allowed to write in a small DSL that can trigger events out-of-band (something like "Oh fuck there's a spider, I'll set up a click spam loop and check in every 500ms").

I think they're doing exactly what you propose? Unless I'm misunderstanding what the Python "fishing scripts" with the timings and timeouts are doing.

https://labs.ycombinator.com/projects/games/index.html#fishi...


One of the celebrity deaths I actually care about. Rest in peace.

> AlpineBSD is an operating system based on the NetBSD kernel with a userspace inspired by Alpine Linux and the objective of making it possible to use as little AI-generated software as possible.

Fucking get over yourself.


Release date? I know someone that has one right now.

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

Search: