Based on a survey of 6,500 tech professionals, these are the top 5 tools people value most: 1. @Linear — Participants love Linear’s user experience, its match to their workflows, and its relative simplicity and focus compared with Jira. 2. @cursor_ai — Cursor is rising at an
CODE
-
New Computer Use Video Course Launched with DeepLearningAI
By
–
We just launched a new video course on how to get started building with Computer Use, in collaboration with @DeepLearningAI.
— Alex Albert (@alexalbert__) 22 janvier 2025
It's the first real course we've made on Computer Use, highly recommend checking it out! pic.twitter.com/kXCkXbeTV3We just launched a new video course on how to get started building with Computer Use, in collaboration with @DeepLearningAI
. It's the first real course we've made on Computer Use, highly recommend checking it out! -
Flowise v2.2.4 Releases DeepSeek R1 and Enterprise Features
By
–
Flowise v2.2.4 is out now with
— FlowiseAI (@FlowiseAI) 22 janvier 2025
🧠 DeepSeek R1 (hosted and ollama)
📈 Rerank-2 by VoyageAI
🗒️ Logs streaming to S3
🔐 AWS Secret Manager for encrypt/decrypt
It's mind-blowing to have the 7B model (DeepSeek-R1) perform on par with O1-Mini pic.twitter.com/QuFpZobKJpFlowise v2.2.4 is out now with DeepSeek R1 (hosted and ollama) Rerank-2 by VoyageAI Logs streaming to S3 AWS Secret Manager for encrypt/decrypt It's mind-blowing to have the 7B model (DeepSeek-R1) perform on par with O1-Mini
-
Remove whitespace from text before passing to LLM
By
–
Could you remove the whitespace? And then do that on every input before passing it to the LLM later. Should be super cheap computationally:
Like text.replace("Legal Jargon", "LegalJargon") -
AI Assistant Now Executes Shell Commands Directly in Chat
By
–
Assistant can now execute shell commands directly in the chat pane. Save time by running commands without leaving the chat. Build more, ship faster.
-
Microsoft UFO: Large Action Models Implementation Guide
By
–
Large Action Models: From Inception to Implementation https://
github.com/microsoft/UFO/
tree/main/dataflow
… https://
microsoft.github.io/UFO/dataflow/o
verview/
… -
OS-Genesis: Automating GUI Agent Trajectory via Reverse Synthesis
By
–
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis https://
qiushisun.github.io/OS-Genesis-Hom
e/
… -
CAG vs RAG vs Hybrid: Choosing the Right Data Approach
By
–
So, Which One Should You Use?
• CAG: Perfect for smaller, static datasets where speed and simplicity matter most.
• RAG: The go-to for large, dynamic datasets where real-time retrieval is a must.
• Hybrid: Why not combine both? Use CAG for frequent queries and RAG for edge -
Context-Augmented Generation: Memory and Scalability Limitations
By
–
That said, CAG has downsides:
• You need lots of memory as you fill the context window at every query.
• You cannot upload your whole million-rows dataset. It must be smaller than the current model's context window (e.g. 128k, 200k… tokens).
• You must host the model -
CAG Preloads Knowledge into Long-Context Model Memory
By
–
On the other hand, CAG preloads all the necessary knowledge into a long-context model’s memory in its KV cache. A complicated way of saying the database here is pre-computed into the model's initial state.