No matter where you are, you can interact with @HyperWriteAI
's Chat features.
INNOVATION
-
HyperWrite AI Chat Features Available Everywhere
By
–
-
Text-to-Music AI Demo Shows Impressive Text Prompt Understanding
By
–
Also check out text-to-music demo by @fffiloni
, I'm still surprised by how nicely it understands the text prompts. https://
huggingface.co/spaces/fffilon
i/spectrogram-to-music
… -

Text-to-Music-Video Generator Powered by Riffusion
By
–
Generate text-to-music-video, powered by @riffusionai and @StableDiffusion
. It works surprisingly well and is able to generate up to 10 second long videos. Come check it out at: https://
huggingface.co/spaces/DGSpitz
er/TXT-2-IMG-2-MUSIC-2-VIDEO-w-RIFFUSION
… -
LEGO Mario Set Combines Real-World Gaming with AI Sensors
By
–
Obsessed with this Lego Mario set, a real-world video game with sensors, world interaction and stateful reactions 😍 pic.twitter.com/lY15m6VFue
— Dr. Angelica Lim @petitegeek.bsky.social (@petitegeek) 16 janvier 2023Obsessed with this Lego Mario set, a real-world video game with sensors, world interaction and stateful reactions
-

AI-Assisted Data Science: Enhancing Productivity in Notebooks
By
–
AI-assisted data science 🤯
— swyx 🐣 (@swyx) 16 janvier 2023
Stay in notebook without breaking flow, retaining full control over the output.
More productive than either human or AI would be alone.
Developers are first to benefit because we can build these things for ourselves before we build for others pic.twitter.com/7cZGa1sCd9AI-assisted data science Stay in notebook without breaking flow, retaining full control over the output. More productive than either human or AI would be alone. Developers are first to benefit because we can build these things for ourselves before we build for others
-
Agent Response Parsing Improvement for Final Answers
By
–
Parsing of agent responses – h/t @krrish_dh Previously, the agent response expected the "final answer" to start on the same line as the "Final Answer" prefix. For longer answers, this sometimes didn't happen We now longer enforce that it be on the same line
-
Wikipedia Search Now Includes Page Attribution for Source Citation
By
–
Wikipedia source information – @rubensmau When you get a document from wikipedia search, it now comes with a `page` attribute (the page it was fetched from) This is needed when doing question/answering with sources (so you can cite the correct page)
-
LangChain introduces multistep SQL chain for database queries
By
–
New multistep SQL chain Sometimes there are too many SQL tables to put information about all of them into context. There's now a chain that: 1. selects which tables are relevant to the query
2. runs the previous SQL chain only over those tables https://
langchain.readthedocs.io/en/latest/modu
les/chains/examples/sqlite.html#sqldatabasesequentialchain
… -
SQL Chain Update: Row Limit Parameter Implementation
By
–
Updated SQL chain – @fpingham Similar to the above, the SQL chain would sometimes fail if the query generated too many rows. @fpingham added a parameter to help limit the number of rows that are returned https://
langchain.readthedocs.io/en/latest/modu
les/chains/examples/sqlite.html#choosing-how-to-limit-the-number-of-rows-returned
… -
Version 0.0.64 Release: Enhanced Robustness for Large Context
By
–
v0.0.64 a bunch of updates making it more robust to large context Updated API chain – @fpingham Updated SQL chain – @fpingham New multistep SQL chain
Parsing of agent responses – h/t @krrish_dh and Wikipedia source information – @rubensmau