Another Dev's Two Cents

Sign in Subscribe

Nish Tahir

https://nishtahir.com

How to use Azure AI Foundry OpenAI Deployments with the OpenAI SDK

Azure OpenAI Deployments are a way to deploy and manage your OpenAI models in Azure. However examples in the dashboard and documentation use the AzureOpenAI sdk. This is fine if you plan to stay within Azure but can be a pain if you plan to switch between other OpenAI compatible

Blocking Spam Email Domains with Self-Hosted Ghost

I noticed an uptick in spam signups on my self-hosted Ghost instance. Specifically those coming from email to SMS gateways[1]. I suspect that they use the email address to send a text message to verify the phone number. I'm not sure how many people actually use these

How to use Bluesky posts as Ghost comments

Today I ran into a couple of interesting posts that focused on the benefits of bluesky as an open platform. One of the use cases shared focused on using bluesky for blog comments[1]. This shows the potential for using bluesky comments as a way to engage with readers that

On Ghost Engineers And Proof or a Lack thereof

I've been watching the media landscape evolve in real time and I feel compelled to share my opinion. I'm not a researcher or journalist, but I have been in Engineering for a long time. I don't intend for this to be an attack on

Reinstalling NVIDIA drivers on Zorin OS

I've run into this issue twice now while using Zorin OS so it made sense to leave notes on resolving them as well as links to resources. The root issue appears to be instability with driver updates. Given that my use case is primarily machine learning, having a

RAG is not just text

Retrieval Augmented Generation (RAG) is a common pattern in AI-powered apps that allows a model to generate completions using context data that might not have been available during training. It's beneficial when working with large language models because it helps the model make inferences on private data such

Model Collapse is an Information Degredation Problem

Model collapse has been all over the news lately citing a paper[1] that was recently published in Nature. The paper focuses on the effects of model collapse which is a phenomenon where a model trained on recursively generated data fails progressively and gets worse over time. "We find

Statistics For Programmers - Naive Bayes Classifier

Putting together everything we've learned thus far, let's build a Naive Bayes Classifier. It is a simple probabilistic classifier that applyies Bayes' theorem. It's a popular choice for text classification problems because of its simplicity and efficiency however it does assume some independence

Statistics For Programmers - Bayes Theorem

Bayes Theorem is a fundamental concept in statistics and probability theory. It provides a way to update the probability of a hypothesis based on new evidence or information. It's particularly useful in situations where have some knowledge about the efficacy of a test or the prevalence of a

Statistics For Programmers - Conditional Probability

The conditional probability of an event is the probability of an event occuring given that another event has occured. The It is denoted as \(P(B|A)\) and is read as "the probability of B given A". That is the probability of event B occuring knowing that event