Home / Companies / Braintrust / Blog / October 2023

October 2023 Summaries

4 posts from Braintrust

Filter
Month: Year:
Post Summaries Back to Blog
We've been working on an exciting new feature at Braintrust that will be announced soon. In the meantime, we've made some user experience improvements and fixes this week, including a resizable experiment sidebar to improve viewing logged data in traces. The update also includes multiple performance optimizations and bug fixes, as well as improvements to tooltips within the web UI. Additionally, Braintrust has been featured on replit.com and sparked debate on Twitter about supporting on-prem for software. The company is an enterprise-grade stack for building AI products, aiming to simplify the incorporation of AI into businesses.
Oct 30, 2023 170 words in the original blog post.
The team at Braintrust has been busy, with many users shipping their Large Language Model (LLM) apps into production and evaluating them with the platform. To make this process more efficient, they have introduced several new features, including an improved prompt playground for managing variables and test cases, and time duration summary metrics to compare experiment results. These updates aim to reduce uncertainty and tedium in incorporating AI into businesses, providing a more streamlined experience for users.
Oct 23, 2023 341 words in the original blog post.
We've shipped a new feature to help debug and observe LLM app pipelines by logging function calls and getting useful traces in the Braintrust UI. Additionally, we made the experiment dashboard customizable, allowing users to select which charts they'd like to see for their experiments. Other updates include a new "text-block" prompt type in the playground, increased default rows per page for experiments, and several UI fixes and improvements. These changes aim to reduce uncertainty and tedium in building AI products with Braintrust's enterprise-grade stack.
Oct 16, 2023 264 words in the original blog post.
Braintrust has released several new features this week, including improved experiment loading times and a new tutorial on finetuning GPT3.5 to write SQL queries. The company also evaluated the Alpaca evals leaderboard in Braintrust, providing aggregated rankings and individual model comparisons. Additionally, Datasets have been improved with display of last edited date and version number, while release notes highlight various bug fixes and enhancements. Braintrust is an enterprise-grade stack for building AI products, offering a range of tools to simplify the incorporation of AI into business operations.
Oct 09, 2023 297 words in the original blog post.