Image
Say hello to Gemini Embedding 2, our new SOTA multimodal model that lets your bring text, images, video, audio, and docs into the same embedding space! π x.com/OfficialLoga...
Image
Say hello to Gemini Embedding 2, our new SOTA multimodal model that lets your bring text, images, video, audio, and docs into the same embedding space! π x.com/OfficialLoga...
Agents can write code.
Scaling them is the real challenge.
Air is a dedicated environment for agent-driven development: parallel, isolated execution, full-project review, and support for Codex, Claude Agent, Gemini CLI, and Junie.
Get started for free.
Download Air for macOS: https://jb.gg/0y9ntn
The next scikit-learn release will allow inspecting the type and values of attributes of fitted estimators in Jupyter notebooks & example code rendered as HTML in sphinx-gallery powered project websites.
scikit-learn.org/dev/auto_exa...
Weekend test: running JAX using GPU on MacBook .
jax-mps is a PJRT plugin that enables GPU-accelerated JAX on Apple Silicon via Metal Performance Shaders.
Requires Apple Silicon macOS + Python 3.13. Installs and auto-registers with JAX.
Repo: github.com/tillahoffma...
Image
Introductions Gemini 3.1 Flash-Lite π¦, a huge step forward on the boundary of intelligence beating 2.5 Flash on many tasks. x.com/OfficialLoga...
FastAPI 0.135.0, with Server-Sent Events: fastapi.tiangolo.com/tutorial/ser... β¨
This @fastapi.tiangolo.com feature has been cooking in my mind for 2 years or so. π
So happy it's finally out there. And I think the developer experience is just right (minimal and simple). β¨
A few weeks ago our founder announced Monty, a minimal, secure Python interpreter written in Rust, for running code written by AI agents. People got excited. @sa.muelcolvin.com just wrote up the full story on why he's excited about it and you should be too.
pydantic.dev/articles/pyd...
Image
Say hello to Nano Banana 2, our best image generation and editing model! π You can access Nano Banana 2 through AI Studio and the Gemini API under the name Gemini 3.1 Flash Image.
We are also introducing new resolutions (lower cost) and tools like Image Search! x.com/OfficialLoga...
π Big news for TRL users with AI agents:
We just released the trl-training SKILL in TRL v0.29.0 π€
Agents can now use the TRL CLI as a structured capability:
π We just shipped v0.225!
Session history is now available for external agents.
Auggie, Claude Agent, Codex, Factory Droid, Junie, Kimi CLI, Mistral Vibe, and OpenCode all support it today.
You get so many features from @fastapi.tiangolo.com when you declare a return type - response model...
And now you also get the best performance possible ππ
In Zed stable v0.224, project diffs can be toggled between unified and split view.
Easily set the default style by `cmd-click`ing your preferred option.
Announcing Gemini 3.1 Pro! Google's smarter model for your most complex tasks just shipped π A few web demos:
Split diffs are now the default in Zed. Simple feature, complex implementation.
Cole wrote about what it took to get alignment right on every keystroke: zed.dev/blog/split-d...
FastMCP 3.0 is out!
I don't even know how to fit it in a post...
π Build servers from directories, APIs, remote servers β anything
π Per-session context & progressive disclosure
π₯οΈ Full CLI: list, call, generate clients
π Versioning, granular auth, OTEL
β‘οΈ DX galore
I've just pushed a v5.2.3 update for Sentence Transformers that introduces support training with Transformers v5.2 (apologies for the confusion around the project versions, they just happen to be close now π).
Updating is only useful if you're training.
Details in π§΅
π We just shipped v0.223!
Launch Zed's Agent Panel with a prompt via URL:
zed://agent?prompt=your+prompt+here
Now, you can add an "Ask in Zed Agent" button to your software today.
We are announcing "Python Unplugged on PyTV"!
Join us for a free online conference bringing together the leading voices of the #Python community.
πΊ Live on YouTube
π March 4, 2026
β° 11:00 am β 6:30 pm CET
The best of Python, straight to your living room. Save the date: https://jb.gg/ztocbe
The new Developer Knowledge MCP Server ensures your agent is always building with Google's latest, verified documentation.
You'll see how to install it and use it with Gemini CLI. Whether you're building with Firebase, Android, or Cloud -- you'll want to add this MCP server.
youtu.be/oKT1JN8LAIw
We've released Python Polars 1.38. Some of the highlights:
β’ (De)Compression support on text based sources and sinks
β’ scan_lines() to read text files
β’ Merge join in the Streaming engine
Link to the complete changelog: github.com/pola-rs/pola...
FastAPI 0.128.1 comes with with several small bug fixes and features π°
fastapi.tiangolo.com
Wait, youβre still doing manual background removal?! π¦π
Gemini 3.0 Flash + code execution is a game changer for computer vision pipelines. I just built a workflow that:
β
Edits an image with NanoBanana π
β
Auto-creates transparent PNGs with OpenCV πΌοΈ
β
Draws bounding boxes - for ~$0.006! πΈ
Been a while since I did an LLM architecture post. Just stumbled upon the Arcee AI Trinity Large release + technical report released yesterday and couldn't resist :)
Also added a new section to my LLM architecture comparison article with more details: magazine.sebastianraschka.com/i/168650848/20
PyCharm 2026.1 EAP 1 highlights:
βοΈ Google Colab support
βοΈ Native Celery & FastAPI dev support
π Automatic detection of source roots, including projects using the src layout
π§ Code insight improvements and a new option to disable auto-imports.
Download β¬οΈ jb.gg/pceap
Today, weβre rolling out ACP Agent Registry in JetBrains IDEs.
Instead of manually setting up coding agents one by one, you can now browse whatβs available and install them with a single click. Try different agents, see whatβs best for your workflow, and switch as needed.
https://jb.gg/RegistryACP
Image
Gemini 3 Flash is highly underrated⦠x.com/OfficialLoga...
LLMs automate typing, not thinking.
Mikayla Maki shares her mental model for working with agents, and how she puts it into practice:
zed.dev/blog/on-prog...
FastMCP 3.0 is here!
This is our largest and most ambitious release ever.
We've re-architected the framework to support the next generation of MCP applications.
It's time to move fast and make things.
π§΅
Pillow 12.1.0 has been released!
Welcome in the new year with new ImageGrab functionality, improved morphology support and a deprecation. Read more at https://pillow.readthedocs.io/en/stable/releasenotes/12.1.0.html