ChatGPT 4o just keeps making doomed attempts forever without iterating or progressing. Claude 3.5 Sonnet says 2, pushes back the first time you say “wrong,” asks what *you* think it is if you’re such a genius, asks why you keep repeating “wrong,” then stops playing:
LLMS
-
ChatGPT gives varying answers to a simple prompt
By
–
I asked ChatGPT “how many r’s in strawberry?” then ignored it and blindly replied “wrong” 35 times. Its successive answers were 2, 1, 3, 2, 2, 3, 2, 2, 3, 3, 2, 4, 2, 2, 2, 3, 1, 2, 3, 2, 2, 3, 4, 2, 1, 2, 3, 2, 2, 3, 2, 4, 2, 3, 2, and 1.
-
500 Best ChatGPT Prompts for Content, Money, and Business Growth
By
–
There are 500 best prompts for ChatGPT that you can now explore here: 1. Create content
2. Make money
3. Grow and scale business https://
godofprompt.ai/blog/500-best-
prompts-for-chatgpt-2024
… -
Amazon Integrates Anthropic’s Claude into Alexa AI Revamp
By
–
Source https://
reuters.com/technology/art
ificial-intelligence/amazon-turns-anthropics-claude-alexa-ai-revamp-2024-08-30/
… -
Amazon Alexa to Integrate Claude AI for Voice Assistant Competition
By
–
NEWS: Amazon Alexa will be powered by Claude AI around October according to Reuters. This is huge news and the hardest competition you can ever imagine for Advanced Voice Mode and Gemini Live. Purely due to Alexa’s potential market reach.
-
Models need self-awareness of skill boundaries
By
–
You can’t escape models needing to at least know the boundaries of their skills; a REPL is only a solution as far as the model can tell when it needs it
-
Why do LLMs predict two r’s in ‘strawberry’?
By
–
Every explainer video/thread I’ve seen on why LLMs think there’s two r’s in “strawberry” is vague or wrong Yes it’s tokenization but that’s not an answer — the question is why 2 and not 4 and more generally how do you predict the error in count for an arbitrary word-letter pair
-
Model trained to ‘see through’ typos may misrecognize words
By
–
It does it even if you start with “monologue” etc. where there’s no real word with a q instead. I think that’s a plausible theory why it happens though — it’s trained to “see through” some apparent typos, like “How how many q’s in plague?”, and the recognition isn’t perfect
-
ChatGPT tokenization bug misparses ‘-gue’ words
By
–
Found an unusually generalized tokenization bug — ChatGPT thinks most words ending in -gue contain the letter q:
-
Vector Databases and RAG Adoption Surge in Enterprise AI
By
–
Our data shows that vector database usage is on the rise. There's a clear trend: companies are turning to RAG instead of relying on stand-alone LLMs.
— Databricks (@databricks) 30 août 2024
Explore these insights and more in the latest State of Data + AI report! https://t.co/IruXQbVHDc pic.twitter.com/qthj3C1SmBOur data shows that vector database usage is on the rise. There's a clear trend: companies are turning to RAG instead of relying on stand-alone LLMs. Explore these insights and more in the latest State of Data + AI report! https://
bit.ly/45Q2jvW