Last night I taught nanochat d32 how to count 'r' in strawberry (or similar variations). I thought this would be a good/fun example of how to add capabilities to nanochat and I wrote up a full guide here: https://
github.com/karpathy/nanoc
hat/discussions/164
… This is done via a new synthetic task
OPEN SOURCE
-
Teaching AI Models New Skills: The R-Counting Example
By
–
-
GLM 4.6 Remains Viable for Coding Agents Long-Term
By
–
GLM 4.6 will continue to exist and be useful for powering coding agents even if every single AI lab goes bust and vanishes
-
Replicate Partners with Stainless API for Next Generation SDKs
By
–
We've partnered with @StainlessAPI to build out our next generation of SDKs. They're the team that helps design and maintain SDKs for companies like OpenAI, Anthropic, and Cloudflare. Together we launched our MCP server, now the Python SDK beta, and soon a new TypeScript SDK.
-
Replicate Launches New Python SDK Beta with Full API Support
By
–
We've got a new Python SDK, now in beta. This new SDK makes it even easier to run AI models from your Python code, and it has full support for every operation in our HTTP API. Release notes: https://
github.com/replicate/repl
icate-python-beta/releases/tag/v2.0.0-beta.1
… -
Anthropic Skills Open Source Licensing Restrictions Explained
By
–
Sadly not all of them Most of them are open source licensed but the document ones (PDF, docx, pptx, xlsx) have a license that says you can look but you cannot reuse https://
github.com/anthropics/ski
lls/blob/main/document-skills/pdf/LICENSE.txt
… -
Skills GitHub Stars Growth Comparison with MCP After One Week
By
–
Skills vs MCP github stars after one week Skills might be growing even faster than MCP did…
-
Deploying Machine Learning Models on Arduino Microcontrollers
By
–
From Blink to Think: Deploying ML on Arduino! At LearnOpenCV, we’ve always believed that AI shouldn’t be limited to powerful GPUs or cloud servers. It should run everywhere – even on the tiniest boards.
Our latest article of the edge devices series, explores exactly that idea. -
Neural Operators and TensorLy Ecosystem at PyTorch Conference
By
–
It was wonderful to have @JeanKossaifi and David present the poster on Neural Operators and tensorly at @PyTorch yesterday. There is no ai+science without neural operators. Check out our rich ecosystem.
-
PyTorch Conference: Neural Operators for AI Science
By
–
My first @PyTorch keynote was almost a decade ago in a small venue. So much has changed. Was amazing to come back to the much bigger @PyTorch conference and talk about ai+science. Check out our Neural Operator library and its latest release https://t.co/CouRPFdF60 https://t.co/bOniHIvZlZ
— Prof. Anima Anandkumar (@AnimaAnandkumar) 23 octobre 2025My first @PyTorch keynote was almost a decade ago in a small venue. So much has changed. Was amazing to come back to the much bigger @PyTorch conference and talk about ai+science. Check out our Neural Operator library and its latest release https://
github.com/neuraloperator
/neuraloperator
… -
PyTorch’s Unexpected Growth While Preserving Core Values
By
–
. @PyTorch has snowballed into something never imagined, while still keeping our core values intact!
feels incredible.
-with @ezyang and @apaszke