jota
8.4K posts
jota
@jp_etraud
mono no aware
the desert of dreams Katılım Ağustos 2021
1.1K Takip Edilen1.9K Takipçiler
jota retweetledi
Today’s Figma MCP update makes it one of the strongest integrations with Claude Code I’ve seen.
You can now use Claude Code to design in Figma with the the full context of your design systems.
Figma@figma
Now you can use AI agents to design directly on the Figma canvas, with our new use_figma MCP tool and skills to teach them. Open beta starts today.
English
Find myself spending less and less time here.
Crypto content has basically gone to 0. Most crypto accounts have switched to normieslop or techslop or claude-written articles that are 700 words of empty nothingness about something random.
Barely ever see my friends’ posts because of all the constant algo changes, and there’s always some random person in my replies asking if a screenshot of a trade setup is an undisclosed shill 💀
Overall just an utterly terrible user experience.
This place was awesome 6 months ago (and even last month wasn’t too bad), but the last few weeks on here have been almost unusable
English
jota retweetledi
this guy has 29 models on huggingface at page 2 ranking. no lab behind him. no sponsorship. $2,000 from his own pocket on GPU rentals. he compressed GLM-4.7 to run on a MacBook and quantized Nemotron Super the week it dropped. all public. all free.
nvidia is a trillion dollar company with hundreds of teams but they are not the ones quantizing models middle of the night and pushing them out before sunrise. if nvidia stopped tomorrow their employees stop working. people like @0xSero would not. that is the difference between a paycheck and a mission.
@NVIDIAAI you talk about making AI accessible. the people actually doing it are right here. 29 models deep burning their own compute with no ask except more hardware to keep going. you do not need to build another program. just look at who is already building for you. one GPU to this man would produce more public value than a hundred internal sprints.
i am not asking for charity. i am asking you to invest in someone who already proved it.
0xSero@0xSero
Putting out a wish to the universe. I need more compute, if I can get more I will make sure every machine from a small phone to a bootstrapped RTX 3090 node can run frontier intelligence fast with minimal intelligence loss. I have hit page 2 of huggingface, released 3 model family compressions and got GLM-4.7 on a MacBook huggingface.co/0xsero My beast just isn’t enough and I already spent 2k usd on renting GPUs on top of credits provided by Prime intellect and Hotaisle. ——— If you believe in what I do help me get this to Nvidia, maybe they will bless me with the pewter to keep making local AI more accessible 🙏
English
jota retweetledi
@perceptis_ai Do you have easy any way to connect the tool directly into Claude? That would be a power move and increase serious distribution for the product. Really cool concept!
English
Real business presentations demand more than good design.
Meet Perceptis AI - built for people who win on their thinking, not their templates.
A prompt becomes a boardroom-ready, editable PPT deck.
Grounded in real research and structured like top‑tier consulting deliverable.
English
@bluewmist Silence and a book, people underestimate how restorative it is when your brain has been busy all day.
English
deploying something soon, made in the UAE, leveraging solana payment infrastructure, to help increase transparency for the regional financial system while the conflict is underway, aim being to help shed light just how resilient this wonderful country (and others like it) are, without opinions and/or conjectures, centered around facts and figures
English
The UAE and Abu Dhabi continue to lead in crypto regulatory environments.
VARA has licensed over 85 companies across advisory, brokerage, custody, exchange, lending, transfer, and asset management.
ADGM in Abu Dhabi has licensed 40+ more and launched the region's first DeFi regulatory framework.
The UAE has created a mature environment where licensed companies can focus on operating.
For Solmate, this reinforces our decision to anchor Solana infrastructure in the UAE.
The UAE continues to lead across the space, all the while @solana continues to become the chosen chain for the next evolution of finance.
English
@CL207 @blknoiz06 oz/nz is where they filmed lotr and you're asking if this is fr Z
English
@blknoiz06 lot of nz / australia do look like that anyways
been for total 6-8 month each and imo its been the best westernized places ive ever been to
English
jota retweetledi
this is the worst local ai will ever be. it only gets better from here.
if you are not expanding your mind with these small models you are missing what's happening right now 99 percent tool call success rate. when steered well with the right skills and a framework like hermes agent the node becomes a cognition layer. not a chatbot. not a toy. an extension of how you think.
i was cranking this node at 35 to 50 tok/s all day on personal experiments and now after all the work is done qwen 3.5 9B is iterating on its own code. the game it created. fixing its own bugs autonomously. and the part you should probably not miss is that all of this is happening on a RTX 3060. not an H100. not an A100. the card most of you have sitting in a drawer right now.
if you just open that drawer and put that intelligence to work every tensor core on that card should be running for you. your work. your experiments. your thinking. you all have it but because nobody told you what this hardware can actually do in 2026 you never tried.
the day it unlocks is the day you test your workload, understand the tradeoffs, debug the loops, and then decide if you need to scale the hardware. there is no point buying 3 mac studios when things done well you can squeeze a similar level of intelligence from 9B compared to 70B. but only when you create the right environment for your model through the right harness.
and let me tell you i have tried claude code as a local harness. i have tried opencode. i have tried various others. somehow i landed on hermes agent and never left. there is something magical going on at @NousResearch. the tool call parsers, the skills system, the way it handles small models natively. nothing else comes close for local inference.
own your cognition. your AI. your agent. your prompts. your experiments. why give them away for free. those are who you are and they don't belong on someone else's servers being monitored.
just give it a shot with your existing hardware. you run into a problem the community will help you. and if you are migrating from openclaw to hermes i will personally help you make the switch.
Sudo su@sudoingX
this is what 12 gigs of VRAM built in 2026. a 9 billion parameter model running on a 5 year old RTX 3060 wrote a full space shooter from a single prompt. blank screen on first try. i came back with a bug list and the same model on the same card fixed every issue across 11 files without touching a single line myself. enemies still looked wrong so i pushed another iteration and now the game has pixel art octopi, particle effects, screen shake, projectile physics and a combo system. all running locally on a card that was designed to play fortnite. three iterations. zero cloud. zero API calls. every token generated on hardware sitting under my desk. the model reads its own code, finds what's broken, patches it, validates syntax and restarts the server. i just describe what's wrong and it handles the rest. people are paying monthly subscriptions to type into a browser tab and wait for a server farm to respond. meanwhile a GPU you can find used on ebay is running a full autonomous hermes agent framework with 31 tools, 128K context window and thinking mode generating at 29 tokens per second nonstop. the game still needs work. level upgrades don't trigger and boss fights need tuning. but the fact that i'm iterating on gameplay balance instead of debugging whether the code runs at all tells you where this is headed. every iteration the game gets better on the same hardware. same 12 gigs. same 9 billion parameters. same RTX 3060 from 5 years ago your GPU is not a gaming card anymore. it's a local AI lab that never sends your data anywhere.
English
you don't have time to follow all Anthropic courses? I did it for you.
~/ prompt engineering is just one layer - context engineering is the full picture
~/ system prompts are behaviour architecture, not preferences
~/ more context ≠ better output
~/ the 4D framework
full breakdown with copy-paste templates ↓
witcheer ☯︎@witcheer
English
@Zeneca @NousResearch Our fix here was to do what they do exactly, so it should hold for now, but i can’t promise reliability in the medium term due to their being psychos - best model, very cruel company though lol
English
jota retweetledi
i get this question a lot recently so let me be clear.
hermes has 11 model specific tool call parsers built in. it knows how qwen, deepseek, llama, mistral format their tool calls natively. openclaw doesn't parse any of that. it expects the API to handle it.
that's why my 9B on a 3060 never drops a tool call through hermes. every single tool call lands clean because the parser understands the model's format not just the API spec.
the openclaw founder joined openai in february and the project got handed to a foundation. hermes is built and maintained by nousresearch, an independent research lab that ships open source models and tools for the community. you decide who you want holding your agent framework.
if you're on openclaw right now hermes already has a migration script built in. i'll help anyone who wants to make the switch.
AGI Mind@agi_mind24
@sudoingX Why Hermes and not just Openclaw? What's the benefits
English