V ❗️💲 I 🪐 N

Who the hell needs to know the price of gas is going up, like you won't know or something. Desensitizing is the funniest op, I've ever seen work.

Stop lying you're making the human race look stupid.

Give my computer a command it does it. Tell the LLM a command it does something. I think the LLM is cool but i have to wrap it with so much just to harness its potential. So much bloat to use it. Fix that shit already. I'm starting to lose faith. I don't ever tell clients to use them for anything but simple tasks. The LLM by itself is poop.

@KevinNaughtonJr Lol

craziest shit just happened i asked ai to do something for me and it couldn't do it correctly so i: 1. googled what i was trying to do 2. read how to do it from docs and other things online 3. did it myself 4. it now works correctly wild experience

Lol

Do you know what this means?

Resonance orchestration

Im hopeful but It will be a while. Im still waiting for that day, but ill never see it at this rate. I prefer evaluating everything, anymore. Building anything is a waste of time and money. Any one can build now. I'm looking for something that actually works, through and through. I run all types of tests. From open source to closed and still while some of you are trying to make some cool shit, it still doesn't work the way you say it does and worst yet you have to pay in time which you never get back and money for this crap. The hammer puts a nail in every single time. That's a fuckin tool. 10x developers my ass. Show me

Lol this app is so funny i haven't seen any ground breaking info yet. Just a bunch of attention seekers.

Billions go into this "training"? what the fuck are they training the models with, they have been the same for a long time now. The only thing i see different is the architecture built around it. Most of that blows too. So what are they really spending that money on.

Anyone: ghost reposts, you get those too.

And then there was a whale

Copy fail exploit=sheesh

Moats & Hoes

7 months left. Technology has changed everything in the past few years. Do you know whats coming next or are you just riding the wave?

No one likes to admit it but ai is a better coder

@VictorTaelin Check out a prototype. Ideaphase.app. @grok what is this? Can it help with @VictorTaelin pain points in their post?

seriously, working with AI is MISERABLE for one and only one reason: having to re-explain the same thing "oh yeah this new session obviously doesn't know what proper case trees are, so let me explain it for the 5000th time in my life" I'm tired AGENTS.md doesn't solve this because it is impossible to fit the entire domain knowledge without nuking the context - it would be 1m+ tokens worth RAGs don't solve this, the agent won't search unknown unknowns SKILLs don't solve this unless I keep like a collection of 1750 skills with specific cuts of domain knowledge for each possible subset of my domain that I might need in a given chat, but that's a lot of manual work recursive LLMs or whatever don't solve this for the same reason, you can't dump a domain book and expect the AGENT will magically guess that it is supposed to search for a specific bit knowledge. unknown unknowns fine tuning doesn't solve this (OSS models suck and OpenAI / Anthropic gave up on user fine tuning) I honestly think a good product around fine tuning on your domain would be a major hit and an underdog lab should take this opportunity

Goblins...

@arb8020 😂

gpt-5.5 prompt for codex seems to have a duplicated line trying to get it to not talk about creatures? Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant to the user's query. [...] Never talk about goblins, gremlins, raccoons, trolls, ogres, pigeons, or other animals or creatures unless it is absolutely and unambiguously relevant to the user's query gh link: #L55" target="_blank" rel="nofollow noopener">github.com/openai/codex/b…

Everyone needs the smartest most capable model to summarize emails.

@sagitz_ Nice find. There are so many fascinating exploits lately. Who would have thought github wasn't secure.🙃

We achieved Remote Code Execution on GitHub - and got access to millions of repositories belonging to other users and organizations 🤯 All it took was a single `git push` Here's how we did it (CVE-2026-3854) 🧵⬇️

Where do you fit in? Im still working on arrogance...

You don't have to listen to none of these guys they are just figuring shit out themselves. Few are actually good enough to land a job. The ones who can don't have time to know what's actually happening. Many have nothing to offer. Few are genuine. They're usually pompous, arrogant, and truthfully losers. You could start now and be ahead of the industry in 6 months. It's just one big, copy paste community, BTW.