muneeb retweeted
"we're learning that there's web standards that actually improve how our stuff works”
Maybe have a scroll through specification.website
muneeb retweeted
ok fine, here's free GLM 5.3 Flash uncensored
~13m TPM shared
~360 TPS peak
use it for cybersec, coding, whatever
live at platform.xplabs.ai
muneeb retweeted
everyone's sharing motion graphic videos that Opus 5.5 made, and it's genuinely insane
everyone says they created it with "one prompt", but my one prompt video looked mid
so i went through a bunch of these videos to see how they were actually made, and found the workflow that works
here's how to generate pro level motion graphic videos w/ opus:
1. get reference videos to direct from -> whatships.com
pick 1-2 videos whose style you want and tell opus to match them. naming a style works way better than describing one
without a reference, opus falls back to its default look: centered text, gradient background, everything fading in
that's why so many of these videos look the same. a reference gives it the pacing, the type and the transitions to copy
2. install @HyperFrames_ or @Remotion so opus can build the video
both let opus write every scene as code and render it straight to mp4. no video editor
without one, opus can only describe a video or hand you a rough html page you have to screen record
with it, every frame is exact, and when you ask for a change it edits one line and re-renders instead of starting over
3. install @21st_dev for high quality components in the video
real buttons, cards and UI components made by design engineers, instead of whatever opus invents on the spot
without it, opus draws your product UI from scratch and it looks off. wrong spacing, placeholder boxes, fake-looking buttons
anyone who's used good software can feel it in a second, and the whole video reads as cheap
4. steps 1-3 were context + setup. now dump all of it into opus
your brand (logo, colors, fonts), screenshots of your real product, the reference video, and a quick braindump of how you see the video
then ask for 3 storyboard variants
without this, opus guesses your colors, your font and what your product even does. the video could be for any startup
with it, it could only be yours. and 3 variants means you pick a direction instead of fixing the first idea it had
5. pick the storyboard you like
ask for one still frame per scene before anything moves. fixing a storyboard is way cheaper than fixing a render
without this step, you only find out scene 4 is wrong after the whole thing is animated, and every fix means re-rendering. a still frame takes seconds to change
6. let claude cook
then give notes like a director: "slow every zoom to 0.7x", "hard cut here", "push in on the button"
without notes, the first render is usually 80% there, and that last 20% is what makes it look pro. vague notes like "make it better" get random changes. camera words get exactly the change you want
everyone has the same model. the context you give it is what makes it look pro
let it cooookk
Pydantic AI agents now run on Jev, the classifier from @typesafeai.
Jev doesn't write text, it answers typed questions. So the output_type you already wrote is the question, and the answer comes back as your model, one confidence per field.
pydantic.io/8iAZ9
muneeb retweeted
I think Stanford's CS336 is one of the best materials to learn LLMs from scratch. I just finished working through it (tokenizer, transformer, triton kernels, distributed training, scaling laws, alignment) and highly recommend it. 🧵 Some notes:
At smaller sequence lengths like 1024, the FFN dominates, not attention, which is a big part of why MoE goes on the FFN. At 16k ctx, attention usually takes over.
Naive DDP on 2 gpus: 54% of each step was gradient sync. overlapping comms with backward: 3%. ZeRO-1 sharding cut peak memory 68.7 -> 47.7 GB.
GRPO: base model with the r1-zero prompt got 0/1300 correct for gsm8k. it gets 224/1300 correct with the 3-shot prompt. RL is most effective when it amplifies signal that's already there.
🔗 check it out: github.com/michaelc-yu/cs336…
muneeb retweeted
Introducing Unreal Agent:
An open-source harness with state-of-the-art cost efficiency
39% cheaper than Codex+Astra on Terminal-Bench 4.0 while maintaining performance
muneeb retweeted
What 🫣🫣
try.cloudflare.com/
What a time to be alive man….
muneeb retweeted
want to understand AI well enough to build with it?
i teach AI at UC Berkeley for people with no programming background.
my slides + class recordings are publicly available:
haas-ai-classes.vercel.app
software basics → ML → LLMs → AI agents
muneeb retweeted
An Introductory Course to World Models, 23 lectures
Free> Get all the Interactive HTMLs, Slides (PDF) & and collection of resources cis.upenn.edu/~cis6280/#cour…
muneeb retweeted
If you’re trying to learn Inference Engineering and want to get some hands-on practice, check out this GitHub repo.
github.com/navaneethkrishnan…
muneeb retweeted
A lot of my LLM inference posts here were explaining how different parts of inference work. but i never really covered what implementing this stuff actually looks like in code. So I’m turning that into a repo. it’s for anyone who wants to learn inference hands-on from zero.
check it out: github.com/navaneethkrishnan…
muneeb retweeted
One of the best in the business!!
Stanford: CME 295 - Transformers & Large Language Models
cme295.stanford.edu
muneeb retweeted
We started to post videos for CMU 11-768, AI Agents!
All of the videos will be posted to this playlist, so please bookmark/follow it if you want to be notified of new ones! I'll also try to post them on this thread too.
youtube.com/playlist?list=PL…
muneeb retweeted
Over 300 original figures!
An Illustrated Guide to AI Agents is now OUT on Kindle and other Ebook stores! Presses are rolling, print copies ship in a few weeks.
@MaartenGr and I spent the last year and a half making the agent stack legible: memory, tools, planning, evaluation, multi-agent systems, and code agents. We're ecstatic to finally be able to share it with you!
Agents are being adopted faster than they're being understood. Our bet is that a small number of concepts will outlast everything else in this field, so we spent the time identifying them and explaining them properly.
Concepts and code. You build a working agent yourself along the way.
Order here:
Amazon: amazon.com/Illustrated-Guide…
O'Reilly: oreilly.com/library/view/an-…
muneeb retweeted
This is arguably one of the best technical books you can read on how LLMs are trained at scale:
> GPU memory and profiling
> tiling, kernel fusion, FlashAttention
> Data / Tensor / Pipeline / Context Parallelism
I’ve already read the online free version, but still had to get the physical copy for the library lol.
You can also read it here on @huggingface: huggingface.co/spaces/nanotr…
muneeb retweeted
Replying to @brankopetric00
Kafka shines at hauling large volumes of data. But for p2p messages or work processed in random order, it's the wrong tool.
I wrote about this a while back: netflixtechblog.com/distribu…
And yes, SQS is a good choice!
This is the only site you need to actually get good at Docker.
It’ll put you way ahead of anyone just watching random Docker YouTube playlists.
And it’s completely free, with 11+ hours of hands-on content and exercises. 🐳
learndocker.online/


































