Reasoning AIs are the future and you can run your own completely off-grid: QwQ 32B on the computer
SmallThinker 3B on the phone All you need to get by if you don’t have internet.
LLMS
-
Run Reasoning AIs Locally: QwQ and SmallThinker Off-Grid
By
–
-
Beginner’s Guide to Agent Evaluations
By
–
Beginner's Guide to Agent Evaluations Evaluating LLMs is hard. Evaluating agents is even harder. But it's important to do so in order to not be flying blind We released a new video tutorial on a beginner's guide to evaluating agents https://
youtube.com/watch?v=_QozKR
9eQE8
… -
Get_Writer Launches Palmyra Creative AI Model
By
–
Great talking with @waseem_s about how @Get_Writer developed its new Palmyra Creative model, which debuted last month.
-
Using Generative AI for Data Analysis Infographic
By
–
#Infographic – Using #GenerativeAI for Data Analysis Source: https://
linkedin.com/posts/razia-al
iani_research-activity-7279851316573560832-SY2M?utm_source=share&utm_medium=member_desktop
… #AI #GenAI #LLMs #Statistics #DataScientist #DataScience -
NVIDIA NIM Microservices Integration in Flowise Platform
By
–
At CES 2025, NVIDIA announced foundation models (offered as NIM microservices) running locally on RTX AI PCs. We’re proud to partner with @NVIDIAAI to integrate NIM into Flowise, enabling developers to build AI applications using local LLMs.
-
LinkedIn Deploys SQL Agent Using LangGraph to Production
By
–
How LinkedIn put a SQL agent using LangGraph into production Data teams often spend too much time helping colleagues find data, creating bottlenecks at companies. LLMs can solve this by making data more accessible to everyone LinkedIn is addressing this problem with their
-
Chain of Thought Prompting in Claude 3.5 Sonnet Models
By
–
Yeah this looks like another version of prompting for chain of thought which is very effective: https://
docs.anthropic.com/en/docs/build-
with-claude/prompt-engineering/chain-of-thought
… It has been "trained in" to some degree in newer models, 3.5 sonnet will usually contemplate a bit before giving an answer to hard questions you ask it but it -
O1 AI Model Tool Integration Capability Implications
By
–
once o1 can use tools its going to be over for you fools
-
PowerInfer Model Uses Extended Thinking for Problem Solving
By
–
this model is by powerinfer, its longer because its thinking through the problem to get to a final answer
-
Grok deviendra le LLM leader en 2025
By
–
Almost nobody agrees with me on this, but Grok will be the leading LLM by the end of the year based on infrastructure alone.