We've also made improvements to performance, including an 87% reduction in dropped frames when streaming large file edits. We are continuing to invest in making Cursor faster and more reliable. See everything new this week:
TOOLS
-
Workspace Search Adds File Include Exclude Filters
By
–
Workspace search now has file include/exclude filters.
-
Cursor Improves Voice Input Reliability With Hold-to-Talk Shortcut
By
–
We made talking to Cursor through voice input more reliable, and added the Ctrl-M hold-to-talk shortcut. pic.twitter.com/QS3Uoiic0h
— Cursor (@cursor_ai) 13 avril 2026We made talking to Cursor through voice input more reliable, and added the Ctrl-M hold-to-talk shortcut.
-
Cursor 3 Agents Split Feature for Multi-tasking
By
–
We've shipped several quality-of-life improvements to Cursor 3. They bring a little more delight when you are orchestrating agents.
— Cursor (@cursor_ai) 13 avril 2026
Just like in your terminal, you can now split agents for multi-tasking in Cursor. pic.twitter.com/ueVGQjjN4pWe've shipped several quality-of-life improvements to Cursor 3. They bring a little more delight when you are orchestrating agents. Just like in your terminal, you can now split agents for multi-tasking in Cursor.
-
Lovable Integrates Databricks for Natural Language Data Apps
By
–
Making Data and AI @Lovable.
— Databricks (@databricks) 13 avril 2026
Lovable now integrates with Databricks, providing a natural language interface that allows anyone—regardless of technical skills—to build live data apps can read and write data stored in Databricks.
Bridge the gap between complex data engineering… pic.twitter.com/GA1iYjMutQMaking Data and AI @Lovable
. Lovable now integrates with Databricks, providing a natural language interface that allows anyone—regardless of technical skills—to build live data apps can read and write data stored in Databricks. Bridge the gap between complex data engineering -
Chandra-OCR-2 OCR Model by DataLab Released
By
–
we used Chandra-OCR-2 by @datalabto
: https://
huggingface.co/datalab-to/cha
ndra-ocr-2
… Full write-up by @NielsRogge
: -
Open source OCR processes 27000 arxiv papers efficiently
By
–
We just OCR'd 27,000 arxiv papers into Markdown using an open 5B model, 16 parallel HF Jobs on L40S GPUs, and a mounted bucket. Total cost: $850 Total time: ~29 hours Jobs that crashed: 0 This now powers "Chat with your paper" on http://
hf.co/papers -
Hermes Agent v0.9.0 – The Everywhere Release
By
–
Hermes Agent v0.9.0 – “The Everywhere Release”
— Nous Research (@NousResearch) 13 avril 2026
Full changelog below ↓ pic.twitter.com/aG5M6owBNSHermes Agent v0.9.0 – "The Everywhere Release" Full changelog below ↓ [Translated from EN to English]
→ View original post on X — @scobleizer, 2026-04-13 19:16 UTC
-
DeepAgents introduces filesystem permissions for secure resource management
By
–
🔒 new in deepagents: filesystem permissions shared resources and org-wide policies are exactly the kind of files you want your agent to read but never overwrite. filesystem permissions let you enforce that with simple declarative allow/deny rules!
→ View original post on X — @langchain, 2026-04-13 19:16 UTC
-
Using AI to Extract Blog Posts From Interviews Efficiently
By
–
Similarly I think there are a lot of interviews/etc which have a blog post that can get extracted out of them and I think an AI can do a very good first cut of that blog post before you give it to a junior marketer for polish/human touch/etc.