A real life preview example of SearchGPT and how fast it is 👀👀👀 https://t.co/D6GM2hD9dO
— 🚨 AI News | TestingCatalog (@testingcatalog) 27 juillet 2024
A real life preview example of SearchGPT and how fast it is
@testingcatalog
-
A real-life preview of SearchGPT speed
By
–
-
Comparing AI search tool output quality
By
–
The answer seems quite similar to what you get from Perplexity. Note that it is a Media tab and likely the full answer might be different
-
Anthropic developing ‘Source Citations’ feature for knowledge base integration
By
–
BREAKING: Anthropic is working on the "Source Citations" feature. It seems it is meant to collect relevant citations from the Project knowledge base, which might be very useful for researchers. It is yet unclear if it can be a sign of a "web search" functionality
-
Project knowledge base limits constrained by LLM context windows
By
–
Currently the size of the project knowledge based is capped by the max context window Hopefully we will get a bigger one soon
-
Claude Projects Harmonize feature for local file synchronization
By
–
A "Harmonize" button allows you to sync Claude Project files with your local copy
-
Anthropic introduces Sync Folder feature for Claude Projects
By
–
Anthropic is working on a Sync Folder feature for Claude Projects There you can select a local folder to get your files uploaded in a batch.
-
Inline advertising within Microsoft Copilot responses
By
–
One more example would be inline ads in MS copilot response (been there for a while)
-
Monetization potential of AI-generated Perplexity Pages
By
–
There you can review the Pros & Cons as well. It feels like an interesting touch to a potential monetisation approach where page authors can potentially insert their affiliate links into their content. Example Page https://
perplexity.ai/page/the-scien
ce-behind-fitness-tra-0XjbHnONRaWzwBUbVBVGlQ
… -
Technical analysis of Perplexity’s search index and crawler architecture
By
–
Building a search index is quite tricky – there are only 3 indexes I am aware of – Bing, Google and Brave where Brave was also relying on Bing for 5% of queries initially. They rather do the same thing that Perplexity does here – a combo of a search index and a crawler on top