Alejandro AO ๐ค
@_alejandroao
AI Education | Developer Advocate @huggingface
574 Following 4.4K Followers
frens at Hugging Face tell me llama app (llama.cpp) has a new home: @Llama_app
Follow & spread the word!! ๐ค๐ฆ
Just a reminder that DeepSeek V4.1 Flash 1017, GLM 5.3 Flash, Qwen 3.8 Next Flash, and even Qwen 3.8 27B are all outperforming (in both intelligence and capabilities) every model that was considered "frontier intelligence" in Xmas 2025 (just 11 months ago)
Opensource AI is on fire
Show more
mad respect for binance
I don't think people realize just how much of an engineering marble DeepSeek V4.1 Flash is, because guess how much RAM you need for 1M context window? For reference Llama 3.3 70B would need around 320gb of RAM.
Qwen 3 8B around 144gb of RAM.
DSV4.1F? Less than 0.9gb.
Show more
Reachy Mini has wheels now!
Our little open-source AI robot can finally explore beyond the desktop.
And that's not all:
๐ฑ New mobile app: no computer needed
๐ NFC hats that unlock new personalities and apps
Physical AI just got a lot more fun.
Watch it๐
Show more
The goat has spoken
great read. how many of the key decisions in your project are made by your agent vs yourself?
turns out more than you think.
In our experiment, analysts used Claude Code to advise a fictional farming co-op on whether to expand a program.
The analysis had four decisions, each with two defensible options. We randomly assigned which ones the agent would lean toward.
Full post:
Show more
this reflects pretty well my experience with these models. great new benchmark!
Artificial Analysis v4.3.2 to v5, AI models re-ranking step by step.
software is dead. long live software!
software is dead. sad.
ICYMI: this checkpoint could easily be a new minor version
๐ DeepSeek-V4.1-Flash-1017 is here!
Stronger benchmark performance, faster task completion, and shorter outputs than the previous versionโa Pareto improvement in performance and cost. Now live on our website, app, and API.
๐ ๏ธ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model.
1/4
Show more
beautiful to see. a new nature of apps being born and defined rn
is agent server a good name?
agent os? agent? agent kernel?
Today we're releasing Carbon-X, a 14B model that brings DNA and natural language together for the first time ๐งฌ
1. Beats every open language model we tested across DNA benchmarks. Within a point of GPT-6.1 Sol at >1,000ร lower inference cost.
2. Mid-trained on 300B tokens of interleaved DNA and text, followed by SFT (without distillation!) and RL.
3. A new hybrid tokenizer encodes DNA using ~3ร fewer tokens than BPE.
4. Gives other models a DNA specialist subagent: Kimi K3 gains 11.1 points when it consults Carbon-X.
5. Runs locally on a laptop with llama.cpp. Apache 2.0. Your DNA stays on your hardware.
Model:
Blog:
Show more
not a fun for @Railway :/ keep it up guys ๐ช
TIL that roon's @tszzl profile pic is that boy form magical school bus
btw, here is the prompt that i used for this video.
"""
consider the documentation of pi-durable (present in this repository). create a motion graphics video that illustrates pi-durable's architecture and system design, and how to use it based on this documentation. feel free to use images from the internet if needed. i added the svg logo of pi to this folder for the video.
"""
the docs in question are my research notes about the package. no skills, no mcps. the model does a much better job with simple prompts.
Show more
i had opus 5.5 distill this 30 min lecture about pi-durable into a 7 min vid with my voice.
> qwen3 tts could do a better job cloning my voice
> the video looks great. i'm working on industrializing these kind of explanation videos.
good starting point, but i still recommend watching the full lecture for a more detailed explainer.
Show more
ds is the definition of openness. thank you
๐ Introducing DeepInfer, our in-house inference framework, now fully open source!
Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. Weโre sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable.
๐
1/4
Show more
i had opus 5.5 distill this 30 min lecture about pi-durable into a 7 min vid with my voice.
> qwen3 tts could do a better job cloning my voice
> the video looks great. i'm working on industrializing these kind of explanation videos.
good starting point, but i still recommend watching the full lecture for a more detailed explainer.
Show more
i just recorded a full tutorial on pi durable
1:48 Checkpoints + crash recovery
8:38 Harness vs. app
13:46 App architecture + storage
19:30 Six setup steps
23:11 Local Qwen + llama.cpp demo + restart recovery
Show more
i just recorded a full tutorial on pi durable
1:48 Checkpoints + crash recovery
8:38 Harness vs. app
13:46 App architecture + storage
19:30 Six setup steps
23:11 Local Qwen + llama.cpp demo + restart recovery
Show more
in a few years, opus 10 will handle all logistics in most companies. while at it it will give you a 3d visualization of the universe at t0+1s and solve a few conjectures formulated by astra 8
Itโd be awesome if logistics software could be visualized and turned into a strategy game.
You manage transportation, routes, and the entire logistics network like youโre playing a strategy game.
Inspired by @DilumSanjaya, I also used Opus 5.5 to build it.
Show more
give your pi-dot an avatar
