Frank Fiegel articles - 12 total
GPT-4.5 Announced: How to Access the Latest OpenAI Model Without Rate Limits
OpenAI's latest research preview, GPT-4.5, marks a substantial leap forward in unsupervised learning,...
How to access DeepSeek r1?
Many people are struggling to get access to DeepSeek r1 at the moment because of the rate limits and...
Building ask-PDF service using LLMs
I wanted to add a feature to Glama that allows users to upload documents and ask questions about...
Implementing Tool Functionality in Conversational AI
As part of building Glama, I am trying to build a deeper understanding of the concepts behind...
Replacing GitHub Copilot with Local LLMs
As part of developing Glama, I try to stay at the cutting edge of everything AI, especially when it...
No Single LLM Can Be Trusted in Isolation
I started building Glama after a simple observation: no single LLM can be trusted in isolation. ...
ASCII progress indicators
I have always been fascinated by old terminal interfaces and wanted to bring some of their charm to...
API for calculating OpenAI and other LLM costs
We are excited to share a new API for calculating the cost of different conversational AI models....
Using LLMs to reduce sign-up & onboarding friction
Something that I think a lot about is what's going to be the role of LLMs in user experience (UX). My...
OpenAI is shockingly good at unminifying code
While browsing the Internet for inspiration, I came across an interesting-looking component. I...
How to price a service that saves hundreds of engineering hours?
I've built a Cypress test runner that completes all tests (no matter how many you've got) in less...