馃殌 big-AGI 1.16.0 - Crystal Clear
Clarity and transparency in your AI interactions.
big-AGI 1.16.0 - Crystal Clear - brings enhancements and new features designed to ensure that every interaction with big-AGI is smoother, more intuitive, and simply better - as we always do. We hope you'll love the updated models across the board, and the new cost tracking (please refresh the models to load the latest prices, now supported on Anthropic, OpenAI, and OpenRouter), which will translate to saving money, as anything that can be measured can be optimized for.
What's Changed
- Chat Cost Estimation: display a cost estimation for supported networks*. hover price for token info
- Enhanced Beam based on your feedback: auto-selection and remembering networks and UX simplifications #470
- Major improvements to the Auto-Diagrams Tool
- Save/Load Chat Files with Ctrl+S and Ctrl+O #466
- @joriskalz: YouTube Transcriber persona: transcribe and chat with YouTube videos (un-hide it from the selector) #500
- @mludvig: 3x faster on Apple silicon with Docker multi-arch builds #507
- More: Perfect formulas/LaTeX rendering #508, soft-wrap code #517, chat text selection toolbar, dark mode fixes #520
- Doc corrections by @dandv and @PrivTEC and in #521 #522 #525
- Updated Anthropic*, Groq, Ollama, OpenAI*, OpenRouter* and Perplexity models
- For Developers: updated LLM data structures
- Full Changelog
New Contributors
- A warm welcome and thank you to @mludvig, @PrivTEC, and @dandv for their first contributions to big-AGI!
In Summary
Transparency and user experience improvements, for an improved quality of life. We are thankful to be able to merge contributions for the community, including a new YouTube Transcriber persona and the faster multi-arch (ARM, x86) builds.
Upgrade today and experience the clearer, faster, and more intuitive big-AGI. Available via code, Docker, or on the free instance on big-agi.com. 馃殌
