for all my nontechnical peers who have been hearing about Jev lately but don't know how it works or what it's useful for, here is the simplest way to understand: our brains have 2 systems: System 1 is the gut-based, reactionary mode for quick decisions and System 2 is for tasks that require deliberate thinking and consideration most AIs you currently use are System 2 models where your outputs are in some format that requires creative thinking (most common form is a paragraph of text) but a lot of our real-world AI work isn't chat-based. It's thousands of tiny judgment calls a day like routing support tickets, flagging risky content, or scoring leads so, using a system 2 model for these tasks is like hiring a novelist to sort your mail Jev is able to do these tasks ~100x faster at a fraction of the cost its only drawback is that it's closed, so the team at @interfaze_ai built an open-source version called Lev, free for anyone to run, inspect, and fine tune (see comments)

Was fun to build it..

I’m going to be presenting an open source Jev alternative on Friday You could basically run it on your Mac for free

We did not create an Interfaze shitcoin. Thanks 👍

Come find this guy at Hack the North if you are interested in joining the team. We pay very well :)

Super stoked that all Merge users can now bring deterministic accuracy to their workflows at a fraction of the cost of LLMs 😁

BrokerPlus takes deals from first contact to submission in record time, using Interfaze to read bank statements, pinpoint exact transactions, and pull fields from compliance forms for easier import into their platform Meet the team changing the Canadian mortgage landscape 👇

If you’re building an AI product and figuring out your backend, come join us. Hopefully, seeing how we’ve approached ours gives you a few ideas for yours

We are now live on the @merge_api Gateway! Gateway lets developers access the best models across multiple providers through a single API. You can now use Interfaze through Merge for deterministic tasks where accuracy and consistency matter. Think vision based tasks like OCR and object detection, web based tasks like search or scraping, and audio based tasks like speech-to-text or speaker diarization. Happy building! Docs: docs.merge.dev/merge-gateway…

Super cool what people are building with Interfaze!

Is this the next billion dollar company? @interfaze_ai

I've been making launch videos like these and want to make more professional ones (and I have a lot to learn) If there are storytellers/ creators who're into motion graphics, storytelling for tech, podcasts etc. I'd love to get you coffee and learn about your processes.

We have tons of GPUs right now and we need them to go brrrrrrrr

one of our customers just hit $100 million in annual run rate in just 8 months, because they were able to engineer a new "iPhone moment": their product is so simple it can be explained in one sentence: Pocket is a portable device that attaches to your phone and takes notes on your daily conversations for you they’ve already sold over 200,000 devices because people understand it’s value instantly where most AI companies try to teach customers an entirely new behavior, Pocket just took something people already do and made it easier tl;dr your product's value proposition needs to be obvious and simple to understand If you’re building something, pitch it in one sentence in the comments for some unfiltered feedback!