Had crons part of langgraph for the last two months
CODE
-
FSM Mental Models for Agent Development and State Management
By
–
#1: i graphs/fsm is useful mental model/devX for building agents (this is a matter of taste though) #2: state management (short memory: easy, long term memory: medium, checkpointing: hard, human-in-the-loop: hard)
-

AI Email Assistant Ambient Agent Open Sourced
By
–
For the past six months, I haven't checked email directly, but rather have relied on an AI email assistant to triage and draft emails for me This is an example of an "ambient agent" We're open sourcing the code today, as well as a hosted version for people to try out
-

Model Validation Techniques: Visual Guide with Code Examples
By
–
Model Validation Techniques, Explained: A Visual Guide with Code Examples https://
bit.ly/41Mj4s6
#AI #MachineLearning #DeepLearning #LLMs #DataScience -

Online Data Science and Machine Learning Modeling Courses Available
By
–
Learn from my 2 online #DataScience #MachineLearning Modeling Courses here: DS 101: https://
aiplus.odsc.com/courses/ds-101
-machine-learning-modelling-in-theory-practice
… DS 102: https://
app.aiplus.training/courses/ds-102
-machine-learning-modelling-in-theory-practice
… ————
#BigData #AI #DataScientists #PredictiveModeling #ML #DataLiteracy #PredictiveAnalytics #IoT @_odsc https://
x.com/KirkDBorne/sta
tus/1786085450861412677
… -

Replit Agent Integrates Slack for Automated Channel Messaging
By
–
NEW: Replit Agent now integrates with Slack. Build apps that can post messages and read history from your Slack channels.
-

Sky-T1-32B: Open-Source Reasoning Model Rivals o1-Preview Performance
By
–
"Sky-T1-32B-Preview, our reasoning model that performs on par with o1-preview on popular reasoning and coding benchmarks."
That was quick! Is this already the Alpaca moment for reasoning models? Source: https://
novasky-ai.github.io/posts/sky-t1/ -
Leveraging Unified Memory in PyTorch with Blackwell GH200
By
–
Totally missed that and that sounds awesome. Genuine question, how do you leverage unified memory in PyTorch though? Was discussing this with a user who was using Blackwell GH200 the other day here:
-

Codestral 25.01 Tops Copilot Arena, Doubles Speed for Code Completion
By
–
Codestral 25.01 is not only on top of the Copilot Arena leaderboard, it's also 2x faster than the first Codestral — that matters a lot for code completion
