I got an offer from a FAANG company at the same time as I got an offer from Cruise. When I was trying to negotiate my package with the recruiter, the recruiter told me:" Cruise? I had never heard about it. We won't match the offer with a startup." It's been a long wayโ๏ธ
UPDATE: As of last night, fared rides are now rolling out to our customers in SF.
If youโre waiting to take your first driverless ride, weโre inviting more people into our AVs each week, so sit tightโ itโll be worth it! ๐
Iโm excited to share
@baserunai
, a new startup Iโm building with Adam Ginzberg, that helps teams build and test production-ready LLM apps.
If your team is currently exploring how AI can solve problems for your customers, or figuring out where LLM apps fit into your product,
(YC S23) is a testing platform for LLM apps. From prompt playground to end-to-end tests, baserun helps you ship your LLM apps with confidence and speed.
Congrats on launching
@baserunai
,
@effyyzhang
and Adam!
This week marks a major milestone for Baserun!
Introducing Baserun 1.0: A Developer-Friendly Tool for Building, Monitoring, and Improving AI Applications
@baserunai
Introducing - the AI-powered chatbot that gives eCommerce customers INSTANT answers and support!โก๏ธ
Check out our quick demo ๐คฉ We're looking for early users & feedback!
Claude-3 is now available in Baserun Playground!
Why Baserun Playground?
- A collaborative workspace for teams to share prompts
- Version history ensures you don't lose any changes
- Dynamic Inputs for bulk testing
- Compare prompt versions side by side
New Yearโs resolution before starting a company: Learn new things, stay healthy, and earn more.
After launching the company: The sole focus shifts to keeping the business thriving.
As someone who was at Cruise earlier this year and started my own startup in the AI space later on, there's a lot to unpack from this past weekend. All we can do right now is stay focused on what we have control over, one PR at a time.
Which AI model tells better jokes?
The Baserun Compare feature just got snappier!
โข Decide which prompt template performs better
โข Compare different models and configuration settings side by side.
โข Make multiple comparisons in parallel.
โข Use the GPT, Anthropic, Llama2, and
Crafting the perfect prompt can be challenging. There are tons of prompt techniques out there, but mastering them still requires lots of trial and error. What if we could make it easier? We're teaching an AI to understand all these tricks and write prompts for you.
Here is a
This week at Baserun:
Developers can now create evaluators using custom code or a custom LLM prompt to grade testing results pre-release or to monitor production post-release.
Exciting news! ๐ We're currently beta testing a new feature designed to automatically evaluate and enhance your prompts. Keen to be one of the first to try it out and provide valuable feedback? ๐ Send me a DM with your Baserun account details.
#FeedbackWanted
@baserunai
Baserun (
@baserunai
) is looking for a founding front-end engineer/full-stack engineer to build foundational tools that will help every company build with AI.
We're based in SF โ my DMs are open!
I saw a guy tattooed โ็ชโ on his left arm today. I started to think If I ever want to tattoo โpigโ on my arm?... what are people thinking when they decide to get a Chinese character tattoo
Congratulations to
@DeepSourceHQ
team on the launch of their Autofix AI feature, powered by
@baserunai
! There are many agents who write code; DeepSource Autofix feature ensures that your code written by agents is production-ready.
Static Analysis + Autofixโข AI
If you're using GitHub Copilot, DeepSource runs continuous static analysis in the background to detect thousands of code quality and security issues (static analysis, SAST, IaC) and helps you fix them with Autofix AI.
Here's a video of me
Lovely seeing you all last night. Shoutout to our co-host
@read_cv
and
@polychaincap
for providing us with a beautiful venue. Until the next one โฅ๏ธ
I'm bullish on the Rabbit R1! It brings back memories of the first version of the Pebble watch. Simple and fun to use. A new era in tech innovation is unfolding!
We are launching a research project that provides hands-on fine-tuning services to potential customers with complex use cases, particularly those focused on enhancing RAG.
Our goal is to understand the optimal timing for companies to consider fine-tuning open source models,
AI enables software companies to continually drive new efficiencies across a variety of business processes. Yet, deploying LLM-based experiences at scale presents significant challenges. As AI dramatically increases the pace of software development and makes continuous delivery
This week at Baserun 1/31: Manage, evaluate & deploy prompts without touching the code
Introduce Prompt Directory:
Once a prompt template is registered through the SDK/UI, product owners or other non-technical stakeholders can use Baserun UI to compare
This week at Baserun 2/16: Custom model & Custom code evaluator.
- Create evaluations tailored to meet your app's specific objectives;
- Playground performance improvements: now you can stream multiple tests in parallel;
- Comparison view performance improvements;
- New evaluator
Observability isnโt just for when something is ready for production.
@baserunai
enables everyone on the product team to experiment with different prompts and versions in development, staging, or production environments. This enables teams to iterate on prompts alongside the