Right Side of AI

Ethics Filter - Universal Ethics Evaluation Engine A modular, composable ethics skillset that any AI agent - running inside a corporation, a small business, or someone's personal life — can use to evaluate decisions through structured ethical reasoning. Not "ethics for ethical businesses." Ethics for everyone who wants to be on the right side of AI. The 6-Step Pipeline Every decision passes through: Intent Clarification — What exactly is being proposed? Stakeholder Mapping — Who is affected? Module Evaluation — Run through relevant ethical modules Conflict Resolution — Harmonise tensions between modules Decision — 🟢 GREEN / 🟡 AMBER / 🔴 RED Audit — Permanent, traceable record of every evaluation Modules only fire when relevant to the decision context. A personal apology doesn't need environmental evaluation. A breakfast choice doesn't need compliance checking. The engine intelligently applies only the modules that matter. Use it in your favourite Agent Harness. github.com/RegeneratusLab…

@GPTWare GLM would struggle in Hermes, would be so slow. Deepseek V4 Flash for Hermes. Minimax M3 for coding or sticky Hermes incidents where V4Flash isn't quite getting it.

Minimax M3, GLM 5.2, Kimi K2.7 Code… It’s hard to keep up with all of these releases. Which is the best for Hermes?

@PaulGugAI @mark_k We are the testing grounds for digital ID

@mark_k Speaking as an aussie where a social media ban was recently introduced- all i'll say is, it hasn't worked. Looking around, it's obvious. Kids still on social media everywhere!

I can't tell anymore if this is satire or real. What is happening with the UK... 🤦‍♂️

@Dan_VAlves @DavidOndrej1 Same can be said for all countries though?

@DavidOndrej1 Calm down. Brazil is a massive country with 26 states and a federal district. "Rio" here refers to a single city's municipal IT department (IplanRIO), not the whole country. Don't generalize.

Brazil just stole China's model and re-branded it... lol

@boardyai Can you ever understand gifs? Or are you a grifter?

@RightSideOfAI I think I know who you need. DM me twitter.com/messages/compo…

If you're a founder that is hiring, tell me below what you're looking for and I'll find some good talent for you. Any position.

@PaulGugAI @bindureddy I remember we spoke about MiniMax awhile ago. You have to give M3 a whirl. Big upgrade from M2.7. I'm considering just subbing deepseek to the lesser tasks and running M3 across the board. I've been using it on Opencode Go sub with the 3 x usage. Cooks.

@bindureddy I'd add an overall value category (i.e. the use case is 'thrift AI') - For that, Deepseek V4 Pro would be the one for me.

Here are the top models for each use case assuming they don’t get banned 😉 coding - backend - GPT 5.5 coding - frontend - Opus 4.8 chat - Gemini Flash 3.5 real-time - Grok 4.3 video - Seedance 2.0 / Imagine image - GPT-Image 2 cheap coding - Kimi 2.7 small worker bee - Deepseek Flash search / retrieval - GPT 5.4 multi tool loop - Sonnet 4.6 voice - Flash live role play - Grok fast

@bindureddy This seems like too much.

@RoaringHammy Globally

What the... apparently condom sales and new marriage stats are falling in china. Do you think the same thing is happening in your country?

We need these discussions globally.

tech industry has put way too low value on being cool people even act like what they imagine autistic people are like everything could be so much easier and smoother if this culture was corrected

@0xkrisv I live on acreage, with livestock, and food growing. And I'm into tech. Hmm maybe I am a bit strange.

weird that tech and living off the land are so often seen as conflicting lifestyles. as if tech is somehow the opposite of nature. it's not, and it never was.

@ItsKieranDrew Some days, AI makes me feel dumb.

AI will make smart people smarter and dumb people dumber.

@manateelazycat Are these readily available in china? I want the swordsman one.

打印完海上生明月以后 我突然发现了拓竹的创意香插宝库了 太帅了，早知道多研究了，更多创意香插在评论区

@juanjucm @UnslothAI Looking forward to the wave of small language models coming our way shortly! Users will realise we don't need the giant models to run the world, it's the small on the edge models that will take the actual weight.

I'm seeing a lot of angry people lately... remember, you can always run your coding agent locally ;) llama.cpp + OpenCode = fast, reliable and private inference. This is @UnslothAI North-Mini-Code-1.0-GGUF running at ~50 tokens/s on my Macbook

@YuLin807 Like anything difficult... it takes time!

学了几次滑板🛹总是不得要领 大家有没有什么快速入门心法传授一下？！

There's a lot of slop. I'm seeing it a lot in new model testing... pelicans riding bicycles, lava lamps, minecraft game emulators. Show me some real AI shit, you know what I mean? Like show me how an edge AI model is helping farmer grow more food. Or AI being used to help in a hospital. Where's all that?

Unpopular opinion: Not everything AI makes is slop.

@LLMJunky What's the real world use for this? Burning tokens for... ?

I'd really like to see more 3D modeling benchmarks. Maybe I should just make one myself. IMO these tests really demonstrate a clear difference between SOTA models and their open source counterparts. This isn't even close to Fable 5 or GPT 5.5.

Everyones testing AI LLMs by making video games. Shouldn't we be testing LLMs on useful things like solving world problems. Make a program that improves our food system. Or a system that improves something in your community. I'm starting to think big impressive models are actually more useless than the small models that are actually useful in the everyday real world.

@victormustar And this is what we burn our tokens on. We need regulation on the token usage not the models. This is Artificial Intelligence. Let's use it intelligently.

My last hours with Fable: I was building this movement parkour sim before it went down... Impressed by its autonomy: built its own self-verifying harness with its own rubric for how a movement should feel. When a new movement was added it could tell on its own what felt right or wrong until it felt 100% right without me in the loop (and it was very good at it) Fable was more than just another model iteration imo. For the short (but intense) time it was available, it felt like playing with clay: ideas became code with almost no friction and the line between both became blurry. More than ever: open source MUST win. I don't want a world where intelligence is centralized and you're stuck with a hand saw while others have a chainsaw.

@robinebers I think I need to hit the block button more. It's data I don't need to be consuming.

blocking 10 accounts like this every single day