swordsith

First thought looking at the first options was I would absolutely never prompt this way. The LLM may as well be a misaligned genie in a bottle, it has to be treated as such.

Personally I've always seen AI 'memory' as a pain point for people in their experience using LLMs than a benefit from the agent remembering the last unrelated thing you were working on. It wastes context similarly to 'skills'. The most efficient workflow imo is having a few well written (not by ai) md files across a clean codebase.

It almost seems like they might've been projecting.. lol

Yeah not telling people you're doing the equivalent of css on their website is diabolical dude. You should be ashamed.

my solution to nasty websites with js ridden everything is to scrape and remake the entirely new dom populate it with only content you verify, sure you might lose some detail but its easy to copy website ui if you desire. can be done with something like tamperminkey or a browser ext

The devil is in the useragent and other request metadata

awful website jfc

ragebait used to be hard to identify

The source of the bloat is less vibecoding and more architecture missteps and reliance on using web interfaces for everything.

Sometimes after a larger source draft with AI before I even touch the program I start to pick up on some of the holes in my prompts caused bugs/unintentional mechanics to be potentially woven in. Knowing what you want and how it should be made is half of it, but if you don't supply the bot with extra guardrails eg. don't modify the contents of x, because of y don't allow z. etc. They will do what you ask of them, usually less than you'd hope.

Saying we're at the Peak of LLMS is like saying we never went further than everest, these are probabilistic state machines sure, but the real value is the effort put into tooling and training these models in RL situations.

Could send random characters along with 'keep going' and it would change nothing, the seed is whats causing deviation between these responses.

Auto is not a model, auto is the mystery box option that cursor gives people who are too slow to read a documentation and flip a few switches. With auto you're going to get routed to any model that happens to be the most available and cheap at the moment. Rather you should specify composer or grok as they both charge under cursors auto category - which by the way can be used just fine through cursors cli and ide. Also auto pool usage isn't infinite, just hard to exhaust.

I'd bet your issues with blender could be fixed with configuration or rebuilding the program with older graphics renderers available, it being open source makes alot of the preference issues with blender resolvable imo.

put my same phone number on 10+ google accounts, if you're skipping this you look like a bot, how should google be able to tell you apart from all of the bots.

Myocarditis and blood clots aren't a side-effect, they are life altering and ending.

why I reject thing that makes other peoples lives easier even if it makes peoples lives easier.

I can only stand to use the cursor CLI at this point, but it's usable I like to be able to switch models when one gets stupid or guard-railed, on the pro plan you get so much usage in the composer 2.5 pool you could just use that your whole sub if you wanted.

They tried but only with a subagent that was not entertained with their attempts. Newer LLMs usually come out of the box with pre-prompts to avoid prompt injection so they don't get pwn'd while browsing the internet for example and reading some text hidden off page.

programmers will get the dark-light mode preference from my browser, and still choose to blind me.

I loved this book, especially the release of tension at the end.

from BAM faq post the other day[0].

FAQ

Q: If you want a resolution, why not just pay the money demanded online?

A: We are completely willing to sit down and figure out a fair, reality-based way to ensure this grandfather is made whole. However, there is a fundamental difference between a good-faith resolution and giving in to a coordinated, viral extortion campaign. We will not reward individuals who use fake delivery uniforms, forged signatures, staged police encounters, and residential harassment to manufacture a storyline for profit. We want to help the family; we will not reward a toxic online circus.

Honestly heartless behavior to treat someone trying to get money for a cancer treatment. I hope they go under.

[0] https://bricksandminifigs.com/blog/blog/2026/05/28/bricks-mi...

DON'T LET THE LIGHT DIE OUT! (bring it back up plz)

Personally I feel a vulnerability in local code (unshared ai slop) is much less likely to be exploited, than for say a npm package update that will pwn you as soon as it loads up.

How long will it be until you can't spin the thread and fabricate your clothes stitch by stitch because you're out of practice?

Nice reusable libraries are still a core part of most AI projects, but honestly I think it's not a terrible approach with all the updating dependency malware issues with stuff like NPM.

Facing reality is difficult for these euro types, they feel an need to to simultaneously hate America while also wanting to be like it.

Claude is notorious in my experience to lie directly to your face (even if its baffling) instead of using the web tool. I'll never prompt it without saying 'use web tool' Its ridiculous.

idc its obviously Ai, your algo is wrong.

Seems like a de-webbed fork of this is a no brainer. its crazy what they think people will just take lying down from a open source project.