Greg Z (@gregzonx) 's Twitter Profile
Greg Z

@gregzonx

Tech Entrepreneur || ML, NLP, LLM || WebDev || InfoSec || Data Management

ID: 357071400

linkhttps://llm.extractum.io calendar_today17-08-2011 20:09:59

510 Tweet

311 Followers

180 Following

EXTRACTUM.IO (@extractum_io) 's Twitter Profile Photo

Exploring LLM Leaderboards: Can we trust them to pick the best model for our projects? #llm #AI llm.extractum.io/static/blog/?i…

EXTRACTUM.IO (@extractum_io) 's Twitter Profile Photo

🚀 New week, new #AI breakthroughs! Our latest roundup of top-trending Large Language Models is out. Discover innovative models making waves in the #MachineLearning community, from reasoning experts to cybersecurity wizards. #LLMs linkedin.com/pulse/top-tren…

EXTRACTUM.IO (@extractum_io) 's Twitter Profile Photo

🚀 Jamba's making waves as the top-trending LLM on LLM Explorer! 📷 Dive into our latest post for expert reviews and insights. Have thoughts on #Jamba? Leave your review on our site! 📷#LLM #AI llm.extractum.io/static/blog/?i…

EXTRACTUM.IO (@extractum_io) 's Twitter Profile Photo

Check out our latest blog for Top-trending LLMs Week#15! Discover CohereForAI's C4AI Command R+ with 90K downloads, JetMoE 8B's economic edge, new entries from Qwen, Turkish & Polish LLMs, Google's Gemma 1.1 7B (IT), and Maxime Labonne's latest project. llm.extractum.io/static/blog/?i…

EXTRACTUM.IO (@extractum_io) 's Twitter Profile Photo

🚀 This week on LLM Explorer, check out the trending Large Language Models from Mistral-Community, Google, and Stability AI! Visit our site for more info and share your insights to guide the AI community. llm.extractum.io/static/blog/?i… #LLM #AI

EXTRACTUM.IO (@extractum_io) 's Twitter Profile Photo

We've just posted about free online LLM playgrounds where you can test various language models without installing them. llm.extractum.io/static/blog/?i… #LLM #AI #LLMplayground

Greg Z (@gregzonx) 's Twitter Profile Photo

Behold, the LLM Explorer Rank! It's like speed dating for AI models, but nerdier. I’m introducing the new way to compare LLMs on #LLM Explorer. medium.com/@mne/developin… Curious how I ended up playing matchmaker for algorithms? The full scoop's on #Medium. #benchmarking #ranking

Greg Z (@gregzonx) 's Twitter Profile Photo

Check #WordPress plugin compatibility before version upgrade wpc.walive.io:33500 and keep you website up and running after upgrade.

Check #WordPress plugin compatibility before version upgrade wpc.walive.io:33500 and keep you website up and running after upgrade.
Greg Z (@gregzonx) 's Twitter Profile Photo

A huge update on #LLM Explorer: new model benchmarks, new filters, UI enhancements. Check it out 👉 llm.extractum.io #llms #ai #genai #llmops #ml #machinelearning #llmapps

A huge update on #LLM Explorer: new model benchmarks, new filters, UI enhancements. Check it out 👉 llm.extractum.io

#llms #ai #genai #llmops #ml #machinelearning #llmapps
Greg Z (@gregzonx) 's Twitter Profile Photo

Here's how you can enhance accuracy in #RAG applications by transitioning from #vector-based search to full-text search. medium.com/@mne/precision… #fts #RAG #embeddings #sqlite

Philipp Schmid (@_philschmid) 's Twitter Profile Photo

Can Anthropic Claude 3.5 sonnet outperform OpenAI o1 in reasoning? Combining Dynamic Chain of Thoughts, reflection, and verbal reinforcement, existing LLMs like Claude 3.5 Sonnet can be prompted to increase test-time compute and match reasoning strong models like OpenAI o1.

Can <a href="/AnthropicAI/">Anthropic</a> Claude 3.5 sonnet outperform <a href="/OpenAI/">OpenAI</a> o1 in reasoning? Combining Dynamic Chain of Thoughts, reflection, and verbal reinforcement, existing LLMs like Claude 3.5 Sonnet can be prompted to increase test-time compute and match reasoning strong models like OpenAI o1.
Greg Z (@gregzonx) 's Twitter Profile Photo

Magic trick: Turn any unstructured text into Pydantic object with structured output support. Available on the local open-source models too. medium.com/@mne/the-magic…