@fidexcode You know their rule only applies to vide CODING apps not apps that were coded using ai right?
English
Cryptlofi
628 posts
Cryptlofi
@cryptlofi
A business owner. Applied technology, Advertising and Marketing.
شامل ہوئے Kasım 2022
382 فالونگ100 فالوورز
@techbromemes My last message to my agent before seeing this meme while it works on fixing the problem
English
Cryptlofi ری ٹویٹ کیا
working as a software engineer at a large tech company in 2026
English
Friendship with buccal fat removal is over.
Now buccal fat injection is my best friend.
Zoomer 🧢@zoomyzoomm
Unreal save from the 1-yard line
English
Cryptlofi ری ٹویٹ کیا
@RearAdBsBlog It makes me happy. I believe we are leaving the age of absolute cynicism and entering an age of it’s okay to just be a good person and live a complex story.
English
I tapped out on “House of the Dragon” during Season One. Wasn’t feeling it. Could’ve also just been GOT fatigue after that show failed to stick the landing.
But I threw on “Knight of the Seven Kingdoms” a couple weeks ago and fell for it immediately. Terrific so far and funny.
English
@ErikVoorhees Very expensive to run. I love Venice but it is not cost effective AT ALL!
English
You can also make an UNCENSORED AI AGENT by simply accessing Venice's API and choosing the GLM 4.7 Flash Heretic model.
No GPU, VRAM, or setup required. Completely private with zero data retention.
Enjoy!
chiefofautism@chiefofautism
i found a way to make UNCENSORED AI AGENT on a RTX 4090 GPU (!!!) with LOCAL 30B model weights this is GLM-4.7-Flash with abliteration, need 24GB VRAM, safety alignment surgically removed from the weights, the model has native tool calling, it actually executes bash, edits files, runs git (1) use ollama to pull weights of GLM > ollama pull huihui_ai/glm-4.7-flash-abliterated:q4_K (2) proxy it to any coding agent via ollama > ollama launch claude --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch codex --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch opencode --model huihui_ai/glm-4.7-flash-abliterated:q4_K (3) have fun
English
@cz_binance I attempted to implement crypto payments into my business but this was the major issue we ran into especially because other clients could see what they were being charged. It quickly became unsustainable.
English
(Lack of) Privacy may the missing link for crypto payments adoption.
Imagine, a company pays employees in crypto on-chain. With the current state of crypto, you can pretty much see how much everyone in the company is paid (by clicking the from address). 🤷♂️
Coin Bureau@coinbureau
🎙️ NEW: CZ AND CHAMATH WARN PRIVACY GAP IS CRYPTO’S BIGGEST HURDLE Binance founder CZ and investor Chamath Palihapitiya speak on the lack of robust, native privacy protections fundamentally limiting Bitcoin and broader crypto from achieving true mainstream ubiquity.
English
Cryptlofi ری ٹویٹ کیا
@dr_cintas Why is it free what data is collected or what do they get out of it?
English
You can now run open-source AI coding agents without paying for API keys 🤯
Cline CLI 2.0 just dropped with free access to Minimax M2.5.
→ Runs from your terminal
→ Parallel agents
→ Works with any editor
Any model you want. 100% Open Source.
English
Ok that's massive
MiniMax has just released a new coding model M2.5:
- 100% open source
- Only 10B active parameters (!!)
- Competitive with Opus 4.6 / GPT-5.2
But 6x cheaper than GPT-5.2 and 17x cheaper than Opus 🔥
And that's not all:
This model is also very good for search, agentic tasks and office work.
So a perfect alternative to SOTA closed models.
I've been using it for the past few days and it's really really good.
We're so back.
MiniMax (official)@MiniMax_AI
Introducing M2.5, an open-source frontier model designed for real-world productivity. - SOTA performance at coding (SWE-Bench Verified 80.2%), search (BrowseComp 76.3%), agentic tool-calling (BFCL 76.8%) & office work. - Optimized for efficient execution, 37% faster at complex tasks. - At $1 per hour with 100 tps, infinite scaling of long-horizon agents now economically possible MiniMax Agent: agent.minimax.io API: platform.minimax.io CodingPlan: platform.minimax.io/subscribe/codi…
English
MiniMax just dropped M2.5:
- 80.2% SWE-Bench (beats Opus 4.6)
- 37% faster than M2.1
- $1/hr at 100 tokens/sec
- cheaper than Opus 4.6
- it’s open source.
MiniMax (official)@MiniMax_AI
Introducing M2.5, an open-source frontier model designed for real-world productivity. - SOTA performance at coding (SWE-Bench Verified 80.2%), search (BrowseComp 76.3%), agentic tool-calling (BFCL 76.8%) & office work. - Optimized for efficient execution, 37% faster at complex tasks. - At $1 per hour with 100 tps, infinite scaling of long-horizon agents now economically possible MiniMax Agent: agent.minimax.io API: platform.minimax.io CodingPlan: platform.minimax.io/subscribe/codi…
English
@session_app I swapped from signal to session about 8 months ago and I love it. But if we had a discord application that would be incredible!!! Especially if we could self host it or something along those lines.
English
@jadennaut @ValourApp Alright I went through a good chunk of the code and feel confident I can get this thing up and running. Do you want me to make a branch with easy to follow instructions or is that something you would prefer to do? I don’t want to do anything that would step on toes.
English
Good morning, Twitter (X)!
We're hard at work fixing a lot of bugs and cleaning up Valour. We don't usually have a lot of traffic, so you guys have found a lot of things hiding under the surface. That's a good thing!
We have a voltunteer team and pay for hosting out of pocket. That means some things may be a little less polished than what a billion dollar corporation can provide, but keep reporting issues on Github and our team will address them as fast as possible.
We love to see all the new faces and we want to make you proud!
English
@cryptlofi @ValourApp If you're brave enough to dig through the code, its possible, but not officially supported or documented yet. We plan to support a both centralized and federated system.
English