Community for Machine Learning
Joined October 2022
- Tweets113
- Following11
- Followers779
- Likes458
Machine Learning Space retweeted
CLI agents need models that understand terminal workflows, not just text completion.
IQuest-Q1 is an open-weights model trained from scratch for CLI interaction. 320B total parameters, 15B active per token, sparse MoE.
Here's what it does. 🧵
Machine Learning Space retweeted
Chat models generate messages.
Decision models make decisions.
Workflow models execute entire workflows in a single API call.
Stop writing orchestration loops around your LLM.
TypeLLM is a workflow model. You declare the decisions, their types and what depends on what. It runs the whole graph in ONE API call.
Think SQL for AI workflows.
Support ticket example:
→ Classify category + urgency in parallel
→ Refund only runs if billing
→ Reply reads category + urgency
Four steps. One call. Typed results.
vs four serial calls:
→ 2.1x fewer input tokens
→ ~1.9x faster
Machine Learning Space retweeted
Google DeepMind is giving Free access to Highest-tier Antigravity for 6 months!
Apply link 👇
Machine Learning Space retweeted
Gemini 4 Argon is globally available!
This is built to solve the hardest problems from start to finish.
Machine Learning Space retweeted
Google DeepMind is giving 10,000 scientists free highest-tier access to Antigravity for 6 months.
This is the agent-first coding platform now running Gemini 4 Argon. Solid chance to push real research workflows without the usual usage limits.
Apply if it fits your work.
We are offering 10,000 scientists the highest usage tier in Google Antigravity free of charge for 6 months. Please apply! forms.gle/WvmBbPvRbpKG1BPn9
Machine Learning Space retweeted
Meet MAI Code 1.1 Flash by @Microsoft
130B parameters model which runs on your local machine.
This is going to change the way we use AI.
Frontier models run locally 🚀
Machine Learning Space retweeted
Meet Kev: the Open source version of Jev.
Train or use pre-trained weights.
100% local and open source
Machine Learning Space retweeted
The ultimate guide to multi-harness RL by @huggingface team!
what is multi-harness RL? expalined in simple words in 🧵👇
Machine Learning Space retweeted
How to Crack the AI Evala Interview?
Check this Free course by @HamelHusain
Last open lesson of the year! How to crack the AI Evals Interview!
AI Evals are now a part of an increasing number of AI job postings, and you're now more likely to encounter them in interviews.
I've helped design quite a few evals interviews, so I know what kinds of traps exist, along with nuanced things companies tend to look for. I'll discuss this, as well as how to structure a take home or report to help you think through the problem clearly.
Tuesday Oct 6, 8:30am PT. This one assumes some basic evals knowledge. Read this first if you're new to the topic to get the most out of the session: hamel.dev/evals-faq
Sign up here: maven.com/p/07e7c7
Machine Learning Space retweeted
Immediate openings at g2i.ai
Bringing on 50 Staff-level Software Engineers this month.
You’ll partner with leading frontier labs on evaluations and dataset creation.
$200–$300/hr
Fully remote
It’s demanding, detail-heavy work definitely not glamorous but the compensation reflects it.
Apply: jobs.ashbyhq.com/g2i
Machine Learning Space retweeted
LUCI Desktop feeds your entire workday straight to your coding agent.
Meetings. Code sessions. Emails. Everything.
Your agent finally sees what you've been doing. 100% local.
This is proper context memory.
Machine Learning Space retweeted
Now Typeless help you write.
Typeless has been very helpful in transcribing in realtime and now it helps you write also.
Good one
One of the features our users love most is Speak to edit.
Select some text and just say:
"Make it friendlier."
"Turn this into a professional email."
"Rewrite this as a viral post."
"Translate this."
But we kept hearing one request:
What if I don't have anything written yet?
So we built Help me write.
Now you can simply tell Typeless what you want to say, and it'll write it from scratch.
We believe voice will become the next major interface between people and technology.
But the real promise of voice isn't just saving time. It's helping us express ourselves better.
Our goal with Typeless is to make voice the most natural way to express what you mean and get things done.
For writing, that means turning your thoughts or intent into clear, polished writing.
Sometimes that means speaking your thoughts and letting Typeless shape them. Other times, it's better to simply express your intent and let Typeless do the writing for you.
Help me write is another step toward a world where you focus on what you mean, and Typeless helps you say it better.
Machine Learning Space retweeted
The best stack is the one you can swap out.
Swapped the model under a running agent. Swapped the retrieval layer. Nothing broke.
That's the test.
Nebius AI Builder Program ships with $400+ in credits and every primitive swappable.
Free to join: dev.nebius.com/builders
🤝 Paid partnership
The Nebius AI Builder Program is now available.
AI isn’t just a model you call anymore. It’s a system you build. And builders, not a few closed labs, will decide what it becomes.
The open ecosystem has all the pieces. We want to make it easier to put them together and start building.
The program is free, with $400+ in credits and discounts, working code and cookbooks, office hours with engineers, and a community to build with.
We’re joined by @NVIDIAAI, @LangChain, @huggingface, @cognition, @OpenHandsDev, @tavilyai, @TolokaAI, @composio, @PrimeIntellect, @MiniMax_AI, @Alibaba_Qwen, and more joining soon.
Join with the link in the comments 👇
Machine Learning Space retweeted
Gradio Docs MCP server + Cursor is a proper time-saver.
It gives your @cursor_ai direct access to the latest @Gradio docs
No more hallucinated UI components from outdated training data. No more copy-pasting API references into the chat
Just ask, and it pulls what you need
Worth the 5-minute setup if you build with Gradio
Machine Learning Space retweeted
Just built Parked.
Snap where you parked. Tap to walk back.
No account. Works inside garages where GPS fails because the photo is the source of truth.
Built this app in 15mins with Rork + GPT-6 Astra. @rork
Machine Learning Space retweeted
Congratulations @MistralAI 🎉
Machine Learning Space retweeted
I just created a brand new voice on @GradiumAI Voice Design and tried it on this Van Gogh painting 🔥
Described the speaker in plain language, heard a few options, kept one in Studio... then ran it on the painting.
This is hilarious ✅
Congrats @GradiumAI on launching Voice Design.
Make your own avatar here: gradium.link/voice-avatar
Today, we’re launching Voice Design.
Write a prompt, create a voice.
Describe the accent, age, gender, and pace your use case needs, and get new voices in seconds, ready to use.
Live and free in the Gradium API and Studio. gradium.link/voice-design
Machine Learning Space retweeted
Python framework for building real-time voice AI agents.
Pipecat handles the whole pipeline:
→ Speech recognition
→ LLM processing
→ Text-to-speech
→ Real-time streaming
Works with Deepgram, AssemblyAI, OpenAI, Anthropic, ElevenLabs, and 20+ more providers.
Build voice assistants, support agents, or AI companions with pluggable components.
Ultra-low latency. WebRTC built in. 100% open source.
