Yes — instead of Markdown, use tags. If you dig through my tweet history, a couple weeks back I posted a conversion prompt that takes a GPT-4-style prompt and converts it to Claude format.
LLMS
-
Big Models: High Performance Comes at High Cost
By
–
Big model, big examples, big success, big expensive
-
Abacus AI Enterprise MLOps and LLMOps Platform Solutions
By
–
#Statistics & #MachineLearning #infographics from @AbacusAI Learn about their incredibly COMPLETE Enterprise #MLOps & #LLMOps Platforms and Solutions at http://
abacus.ai
————
#BigData #DataScience #AI #ML #DeepLearning #DataScientists #LLMs #GenerativeAI #NLProc #GenAI -
Zero-Shot Methods to Enhance Foundation Model Performance
By
–
Want to get more out of your foundation models? Join Dyah Adila's upcoming talk on zero-shot methods to enhance embeddings – no fine-tuning required! Free & online! Register now: https://
snorkel.ai/event/better-f
m-performance-sans-fine-tuning-research-talk-with-dyah-adila/
… #NLP #AIResearch -
Last Chance: 30% OFF ODSC East AI Conference Registration Today
By
–
Don’t miss your last chance to take a deep dive into the cutting-edge of #AI for 30% OFF #ODSCEast registration. Last chance for best price Register now! 30% OFF ENDS TODAY! https://
odsc.com/boston/ @_odsc ————
#ODSC #DataScience #AI #ML #DataScientists #GenerativeAI #LLMs -
Technical behavior of file uploads in ChatGPT
By
–
I would doubt that. It is more like a different source from where the file can be uploaded once and stored on the ChatGPT side afterwards. If remote doc is changed, you will need to reupload.
-
Quiet-STaR: AI Models Learn to Think Before Responding
By
–
Stanford researchers just developed Quiet-STaR, a new training method that enables AI models to ‘think’ before responding.
— Rowan Cheung (@rowancheung) 22 mars 2024
When applied to the Mistral 7B language model, Quiet-STaR nearly doubled its scores on math and common sense reasoning benchmarks. https://t.co/jv02P5yStXStanford researchers just developed Quiet-STaR, a new training method that enables AI models to ‘think’ before responding. When applied to the Mistral 7B language model, Quiet-STaR nearly doubled its scores on math and common sense reasoning benchmarks.
-
Sakana AI Releases Three Models Using New Evolutionary Training Method
By
–
Sakana AI just released three new Japanese AI models using a new "Evolutionary" training method.
— Rowan Cheung (@rowancheung) 22 mars 2024
If scalable, this new method could suggest a new alternative training path for AI models.
Going in depth in the newsletter tomorrow: https://t.co/Gm5KwesnA7 https://t.co/AUpbwS9dhSSakana AI just released three new Japanese AI models using a new "Evolutionary" training method. If scalable, this new method could suggest a new alternative training path for AI models. Going in depth in the newsletter tomorrow: https://
therundown.ai/subscribe -
GPT-5 Leaks Reveal Mid-Year Release and Agent Capabilities
By
–
New leaks from internal sources revealed details for OpenAI's upcoming GPT-5 model capabilities and timeline. The release timeline is tentatively slated for mid-year, with sources saying GPT-5 is "materially better" and can call AI agents. More details: https://
therundown.ai/p/gpt-5-rumor-
mill-ignites
…