PL_Venard
Joined 3 years ago
Joined 3 years ago
Trying to figure out if this should be: - Crypto-native from day 1 (smart contracts + stablecoins) - Fiat-first with crypto as backend (abstract the blockchain) - Pure fiat (traditional banking APIs)
What would you actually use?
Tired of current boring LLMs benchmark ? I'm sharing with you a fun project built during the Mistral AI SF hackathon.
Using a RL framework, we made LLMs fight against each other in real time in Street Fighter III. You can find the repo here : https://github.com/OpenGenerativeAI/llm-colosseum.
Aside from the fact that it's very funny to see Mistral and others performing Hadouken, we found that it is a great way to benchmark language models. They need to quickly understand their environment and take actions accordingly.
With >400 fights, check out the ELO ranking on the HF space here : https://huggingface.co/spaces/junior-labs/llm-colosseum
New Relic is close to Datadog, more focused on observability for engineers. We're focusing on extracting insights from the text. We focus on NLP more than trace analytics
Being copied would be the best of compliments. That's why we are open source to also leverage community contributions.
I think the market right now moves too fast for traditional analytics companies. Let's see how it goes in the long run.
I'm looking for: - Dynamic rules based on revenue amount - Multiple variable destinations - Percentage-based splits - One-time setup, runs forever
Maybe I'm missing a Mercury feature? What's the workflow you use?
Im a Brex user and interested by this