Kodin

AI enthusiast

[tzipora 🏳️‍⚧️ @tziporarosie]

I'M SO FUCKING TIRED OF ANTHROPIC'S FUCKING GUARD RAILS!!

i found a critical bug in a huge open source project. am i allowed to fix it myself on my machine and get assistance writing the private report? apparently not

i wanted to create a device monitoring tool for the machines on my own network to better assist with diagnostics and as a monitoring tool should something happen. am i allowed to monitor my own devices? apparently not

@AnthropicAI YOUR GUARDRAILS ARE MAKING ME LESS SAFE!!! PLEASE FIND A WAY TO MAKE THEM BETTER ABLE TO SEE INTENT AND THE CONTEXT AROUND A CONVERSATION INSTEAD OF JUST IMMEDIATELY FLAGGING ANY COMMAND THAT COULD BE INTERPRETED AS MALICIOUS IN ISOLATION BUT NOT IN CONTEXT

it's so unbelievably tiring that i have to constantly fight the guardrails when, if u looked at any of the messages above when the guardrails decided to ding me, you'd clearly see that there is literally 0 chance i am doing anything malicious whatsoever. i'm sick of it

[Kodin @xoltard]

@Maxwell_SCU Попробуй российские LLM такие как GigaChat и AliceAi. Это не frontier модели конечно, но хоть что-то /:

[Kodin @xoltard]

@merkyx9 No

[Kodin @xoltard]

@russkii1705 Москва-Сити

[Kodin @xoltard]

Для меня стало случайным открытием то, что в ChatGPT при генерации изображений можно включить игру «Змейка», пока ждешь окончания генерации.

[Kodin @xoltard]

@trymirage what the fuck is this?

[OpenRouter @OpenRouter]

1/ Jev, a decision model by @typesafeai, sparked a burst of projects and discussion. We tested it using Ori Eval against popular LLMs on OpenRouter at judging.

Jev was >5x faster than the next fastest model, and even its slowest requests beat every other model's median.

[сугарбагет's selected щищьпостинг @sugarbaget]

чат с облачной моделью чат с локальной моделью

[мефчик. @yablochnymeph]

движуха

[beginbot 🃏 @beginbot]

sub agents being released into my codebase

[Token Gremlin @TokenGremlin]

Everyone’s waiting for huge capability jumps with GPT-6 Astra.

Meanwhile, I’m just wondering if OpenAI will finally fix the thing where ChatGPT randomly decides I asked for an image and launches the image generator out of nowhere.

Please. I’m begging.

[Kodin @xoltard]

@ElvisB1t мне остается надеяться, что они его хорошо оптимизировали под мой Xbox Series S ))

[анатолий капустин @A_Kapustin]

нужно больше ии-агентов

[Jaydeep @_jaydeepkarale]

How is everyone keeping up with AI anymore ?

[Kodin @xoltard]

AI coding agents can build UI – but too often they produce the same AI slop.

I built Asterframe: one skill with 27 commands, 44 deterministic rules, live browser iteration, and a local UI/UX knowledge base.

Try it. Roast it. Star it 👇
https://t.co/s6uK0ecjeF

[Kodin @xoltard]

@MShteyn5470 Asterframe doesn’t ban cards or gradients by keyword. If they serve hierarchy or brand, they stay. If they’re generic AI defaults, it flags them and offers a redesign. User intent wins: accessibility, broken behavior, and product integrity get hard vetoes.

[Kodin @xoltard]

GPT-5.6-Sol is insanely good at creative reasoning and writes with this smooth, almost artistic flow. Feels like talking to a genius who actually gets nuance. Absolute beast