
Full-time Python Engineer - Sharing daily insights on Python, ML and AI. - DM/[email protected] for collaboration - Open for opportunities
Remote
Joined July 2022
- Tweets6.8K
- Following224
- Followers104K
- Likes10.7K
Python Space retweeted
X just made mutuals way more valuable.
Copy link weight dropped to 0. Mutual replies now hit 20.0 the highest positive ranking signal.
Stop chasing likes. Start building real relationships. Your mutuals are your biggest growth lever right now.
Python Space retweeted
Dreamina and CapCut have joined forces, bringing an exciting new perk to give CapCut Pro subscribers even more creative freedom! 🚀
Every qualifying user scores incredible rewards: up to 10 free Seedance 2.0 generations, extra credits, plus a full month of Basic for just $0.29 if it's your first time using Dreamina.
dreamina.capcut.com/sv2/ZSpH…
#DreaminaPartner
A fresh demo is easy. Adding a feature to someone else's codebase is the real test.
That's where I'd put LongCat-2.5 from @Meituan_LongCat 🐱
Take an existing dashboard, add search and filtering, then check if the charts and export still work.
I'd look at:
→ Which files it changes
→ Whether the feature actually works
→ How much cleanup I need to do
The tech blog talks about training on long-horizon tasks and turning real agent failures into verifiable training tasks. Curious how that holds up in everyday project maintenance.
API pricing is unchanged from LongCat-2.0:
→ $0.30 per 1M uncached input tokens
→ $0.006 per 1M cached input tokens
→ $1.20 per 1M output tokens
There's also a 50M launch trial token pack for $1.90 ⚡️
Try it: longcat.ai/platform/product?…
Introducing LongCat-2.5, our latest natively multimodal agentic model with 1.6T total parameters and ~48B active.
Built for long-horizon agentic tasks, it brings stronger visual understanding and agentic coding to work ranging from complex coding projects to visual coding such as creative design and 3D tasks.
Learn more about LongCat-2.5: longcat.ai/blog/longcat-2.5/
Python Space retweeted
Your agent works in the demo. Then a real user shows up 😅
Plurai Simulation is now free, and it lets your agent fail before your users see it.
→ Digital twin of your agent and its tools
→ Simulated users that hit the edge cases
→ Evals on actions, not just replies
→ Fixes you can verify
→ Replays of production failures on every new version
Works right inside Claude Code, Codex, and GitHub Copilot.
Nice launch @pluraiAI ⚡️
Big day for us at @pluraiAI ! Plurai Simulation is live and free for every AI engineer.
AI agents look great in demos. Until real users break them.
So we built a world where your agent can fail, learn, and get fixed before your users ever see it.
→ Digital twin: Your real agent, its tools, and environment recreated from your code
→ Simulated users & tasks: Realistic users, tasks, and workflows that push your agent into the edge cases that matter
→ Auto evals: Check what your agent actually did, not just what it said
→ Verified fixes: Every failure comes with the run that exposed it and a fix you can verify
→ Replays: Turn any production failure into a simulation and replay it against every new version of your agent
All inside the coding agent you already use: @claudeai code, @OpenAICodexCli , or @GitHubCopilot .
Start simulating for free: simulation.plurai.ai/connect
Qwen4-Max-Preview is now available in Alibaba's coding agent Qoder, with a limited-time 80% discount ⚡️
I put it to the test with one prompt: build an interactive mechanical keyboard in the browser, with keys that press down and click sounds. @Qoder_ai
Python Space retweeted
Qoduck has officially been unveiled as Qwen4-Max-Preview in Alibaba's coding agent Qoder ⚡️
It's now available in Qoder with a limited-time 80% discount.
I tested it with one prompt: building an interactive 3D solar system right in the browser. @Qoder_ai
Gemini for Healthcare 🚀
Today, we’re announcing Gemini for healthcare.
This newest addition to our suite of purpose-built industry solutions extends the Gemini agent to health systems and health plans.
Learn more → goo.gle/4zf0s11
AI agents can query data—but do they understand what it means?
NVIDIA’s open-source Auto Ontology gives agents a semantic layer to reason about trusted metrics, entities, and relationships, so answers are grounded in the right definitions.
Retrieval is only the start
100% Open source
Python Space retweeted
I gave WorkBuddy one prompt: build a 3D under water scene.
All generated in one shot.
The final video is below.
Cursor killed localhost:3000
Build apps and share them with link to anyone using @cursor_ai
Google just upgraded Flashcards 📚
→ Flashcards now include images
→ Optional stopwatch to test your recall
→ Study reminders on mobile, so you actually show up
Visual memory, timed practice, and a nudge to stay consistent.
No more excuses before exams @Gemini_Notebook
Python Space retweeted
Build live apps in Cursor!
Share with anyone for FREE! No need to worry about where and how to host your first app. @cursor_ai
More details 👇
Cursor just made sharing apps way simpler 🚀
Build a live app right inside Cursor, then share it with a single link.
No deploy setup. No extra tools. Just build and send @cursor_ai
Meet Gemini Omni 1.2 Flash from @GoogleDeepMind
Faster, cheaper, and longer video clips.
→ 30% lower cost: draft at 360p or 720p ($0.07/s), upscale to 1080p or 4K
→ Clips up to 15s, or any exact length from 3s to 15s
What else you need?
















