고정된 트윗
Okay, we made our first proper video 😄 ☕
It's about what we're building and why it matters 🫶
No big pitch. Just something we genuinely believe in.
Would love to know what you think 👇 @GetCoffeeOnMe
English
Coffee On Me
3.2K posts
Coffee On Me
@GetCoffeeOnMe
The simplest way to tip, reward, pay it forward with crypto. Turn a 👍 into a ☕️✨!
Coffee City 가입일 Ocak 2026
685 팔로잉691 팔로워
i didn’t even try fable 5 yet lmao
every time new model comes out i usually forget cause the current model i am using is so good
then when i am auto pushed to the next model its somehow even better
but HOW much better is fable 5 to cause this…
Anthropic@AnthropicAI
The US government, citing national security authorities, has issued an export control directive to suspend all access to Fable 5 and Mythos 5 by any foreign national, whether inside or outside the United States, including foreign national Anthropic employees. The net effect of this order is that we must abruptly disable Fable 5 and Mythos 5 for all our customers to ensure compliance. Access to all other Claude models is not affected. We apologize for this disruption to our customers. We believe this is a misunderstanding and are working to restore access as soon as possible. Read our full statement: anthropic.com/news/fable-myt…
English
@GetCoffeeOnMe @Megatron_ron Yeah that crypto is really working out for ya 👌
English
❗️Please all report @frontlinek1t the Kenyan scammer impersonating my account!!
Please also confirm that you are following my real account @frontlinekit ❗️❗️❗️
English
Fable is banned. Long live local AI.
Full episode breaking down exactly how to get good at local models. the runtime, the hardware, quantization, connecting it to Hermes agent and local AI startup ideas (25 minutes)
GREG ISENBERG@gregisenberg
The takeaway from Fable 5 being BANNED by the government: GET GOOD AT LOCAL MODELS SO YOU HAVE 100% CONTROL. My entire weekend was going to be building my craziest ideas with Fable 5. That's now cancelled. So instead of building with Fable this weekend, I've decided I'll go deep on local models: 1. Start with the runtime. Download Ollama or LM Studio first. This is the thing that actually runs models on your machine. 2. Match the model to your hardware. A model's size is measured in billions of parameters (7B, 32B, 70B). Bigger is smarter but needs more memory. Rule of thumb: a 7B model runs on almost any laptop, a 32B needs a good Mac with 32GB+ RAM, a 70B needs serious hardware like a DGX Spark or a maxed-out Mac Studio. 3. Know which model for which job. Qwen 3 is the best all-around choice for most tasks. DeepSeek for reasoning and coding. Gemma 4 when you need something tiny that runs on a phone. Llama when you want the biggest community and the most fine-tunes. 4. Quantization. You can shrink a model to run on weaker hardware with barely any quality loss. Look for versions labeled Q4 or Q5. This is how a model that "needs" a server runs on your laptop. Learning this one concept changes everything. 5. Connect it to your agent. Point Hermes or your agent stack at a local model. 6. Context window is your real constraint locally. Cloud models give you huge context for free. Local models make you pay for it in memory. A bigger context window eats RAM fast. Keep your sessions tight and your prompts lean or your machine chokes. 7. Learn to give local models tools. A smaller local model with web search, file access, and code execution beats a giant model with none. The capability gap closes fast when you wire up the right tools. The model is the engine but the tools are the wheels. 8. Fine-tuning is more accessible than you think. You don't need this on day one, but know it exists. You can take an open model and train it on your own data so it gets good at your specific domain. I'll probably do a breakdown at some point on this @startupideaspod if people are into it. The lesson from this ban is basically don't build your entire workflow on something that can disappear with a single letter. Own part of your stack. Local models are insurance. It reminds me when people realized they don't own social media accounts. And then you saw people build email lists etc. I remember running a startup and my biggest traffic source was organic FB. All of a sudden, algo changed, and I lost 99% of my traffic. Same sorta moment (but bigger) for AI. This is a wake up call.
English
It's good to have Casillas as your idol but never have his mentality
Football might not like you
Madrid Xtra@MadridXtra
🗣️ David Raya: “My idol is Iker Casillas. He has done a lot for Spain NT and Real Madrid. I always looked up to him.”
English
@sflorimm The question is who is NOT building with AI now, probably not many people right?
English
GN fam 🌙
Charts can wait.
Take a break, enjoy the weekend, and spend time with the people who matter most.
See you all tomorrow. ☕🚀
English
Below 18K followers?📈
Type = 'Hi"👋
We'll f0ll0w you back instantly!💫🔔
English
BREAKING: President Trump says a deal with Iran is scheduled to be signed tomorrow, immediately reopening the Strait of Hormuz.
English
@KobeissiLetter Small businesses don't lie. They hire when they're confident and freeze when they're not. Right now? They're frozen. Q3 will tell the story.
English
The US job market is showing further signs of weakness:
Only 9% of small business owners said in May that they plan to hire over the next 3 months, the lowest since May 2020.
Excluding the 2020 pandemic, this is the lowest reading in 10 years.
Small business hiring plans have trended lower over the last 6 months.
Historically, this has been a leading indicator for nonfarm private payrolls by roughly 4 months.
This comes as small firms account for ~46% of all US private sector employment and suggests that private payroll growth could turn negative as early as Q3.
Hiring demand among small firms is weakening.
English
@hellerincrypto Looks like someone is trying to grab your foot!
English
