Viewing profile — anagri

Bodhi Chat is a demo chat app that connects to Bodhi App running locally on your machine. The connection to Bodhi App is completely secure and backed by OAuth 2.1 PKCE standards. W…

Hi HN, Bodhi App is an open-source local LLM inference solution that takes a different and simpler approach. Instead of re-inventing the wheel, it leverages existing, tried and tes…

@kaiwren thanx for shoutout, looking forward to your feedback

@nandx thanks for shoutout, more features coming soon, feel free to raise issues or feature request using GitHub issues. Thanx

@kartik7153 - looking forward to your feedback

@irfn - that's an interesting idea. will definitely try to create benchmark using my local M2 machine and llama3-7b, just for comparison. yes, ollama and Bodhi App both use llama.c…

thanks @abhinavrai, looking forward to your feeedback, hope you get to use it when you are developing GenAI apps locally as well.

thanks @akashkahlon, looking forward to your feedback

Hi HN, I'm excited to share Bodhi App, a tool designed to simplify running open-source Large Language Models (LLMs) locally on your laptops. While we currently support M2 Macs, we …

so the splash image is generated by midjourney. @levmiseri are you using APIs, or have fine-tuned prompts for each of the location? do share these as well. the github doesn't inclu…

agree you cannot run gumroad like financial transaction business without licence and agreement with stripe. it is bound to be closed down on short notice, and all the earnings will…

just glad that the 2019 IPO didn't materialize, otherwise the innocent retail shareholders would have paid for all the nuisance

++ good problem to solve, nice personal story, but disappointed it is translating into clickbait+data scraping

++ wonderful personal story, but doesn't look like it is translating 100% into empathy.

The X86 vs ARM makes for such a great story. One prefers locking and complicated instructions, the other is designed with open and simplicity. At one point, Intel seemed to be domi…

With LLMs/ChatGPT, i would prefer fine-tuning a model and have it auto-generate bash commands with my natural language description. I remember, I used to keep a diary with landline…

we need ML GPU workload standardization, and more options to chose from. Sucks being held hostage by Nvidia. No ML GPUs available in my country, and waitlist goes in years.

do you have a Mac installer available? also you need a designer. the website looks like from the 2000s. thanks for sharing the app.

read sapiens and other books by yuval noah harari, and later there were articles that many things he claimed in his book were incorrect, or later proven to be incorrect. always blo…

very impressive, the last demo of a working crank-shaft-engine shows you can use it to make complicated models as well. great start, best wishes with the project, looking forward t…

Each company have different motivations. For e.g. Basecamp moved to save cost. Working in Enterprise, I can share hybrid model works best for multinational. If they are going into …

Congrats on the launch. How is it different from - https://chatbase.co/ https://sitegpt.ai/