Moving tryingopen.com model router to d1 by @liquidai running on jetson orin nanos @NVIDIAAI

Self host AI chats on your device or your google drive. One click, no login, zero data retention, free. Try it on Trying Open from @offlinebase, link in thread We're trying to figure out ways to improve privacy and reduce the amt of places your data lives.

@typesafeai Jev for hybrid model routing (local, cloud, edge) Trying to make local AI products good enough for all @offlinebase Thanks @ngrokHQ ai gateway, @OpenRouter, and @liquidai for the models. If it can be more private, it should be. If it can be smarter, it should be.

If you want to try any open model for free, check this out tryingopen.com/

Had a great time at @cerebras cafe compute with @habodoni @electricaliee and @Norminican at the @datadoghq office Thank you to the hosts @zhennydez @MilksandMatcha @thorwebdev and more.

In light of the @GroqInc and @nvidia news, I am going to start posting more publicly about a personal project I am working on: Augment - augmenting.work/ Here's a demo of me making a website on Augment using @Kimi_Moonshot running on @GroqInc . Less than 10 seconds to generate. I made a very simple website for the sake of the example. I think current vibe coding tools are a bit too slow to iterate comfortably given the fact that it may or may not do what you want, but you have to wait ~ 2 minutes to find out (and potentially spend money on tokens that wound up making it worse). I also think deep research queries take a little too long for most folks to casually use. Shoutout to @perplexity_ai for how well they do around this. You can use open source models on @GroqInc , @cerebras , and LLMs from the major labs as well.

Working on a small project to demonstrate the value of faster inference augmenting.work/ Thesis: Frontier models have pretty fast inference, though not fast enough for test-time compute/reasoning and 10+ tool calls. If we are to augment with AI and save time, let's not create a new type of down time... waiting for responses. We used Cerebras as our inference provider to create websites, analysis, and textbook chapters within 2 seconds. We typically hit around 2000 tokens/s. Details: Using Cerebras and Groq as inference providers. Models - GLM 4.6, GPT-OSS-120B, Qwen... Horrible demo video below. Only the typing is sped up. I am still working on this. I just wanted to start posting updates for posterity because @GroqInc and @IBM partnered after I started this and I don't want to miss anymore news regarding the benefit of fast inference when it comes to tool-calling, Reasoning, Enterprise, and healthcare need for speed.