... ...

AIpplier

An LLM-Based Web Automation Agent for automating job applications on popular job boards. Built Using Langgraph, Playwright and GPT4-O. Try it out here

<span title='2024-10-15 04:14:46 +0100 +0100'>October 15, 2024</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;23 words&nbsp;·&nbsp;Damilola John
Vanitas Still Life with a Candlestick, Musical Instruments, Dutch Books, a Writing Set, an Astrological and a Terrestial Globe and an Hourglass, All on a Draped Table by Evert Collier

Zeeno - Find books by describing them. A personal librarian for discovering books

Find books about topics/ideas in your head A recommendation service that let’s you find books about any topic or ideas you are thinking about by describing them in natural language. Github repo Link

<span title='2024-09-15 04:14:46 +0100 +0100'>September 15, 2024</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;33 words&nbsp;·&nbsp;Damilola John

TraceRoute

Tracking a packet from source to destination. A tool for tracing the path followed by an internet packet across the internet implemented in python. Inspired by TraceRoute the Unix tool. github

<span title='2024-08-15 04:14:46 +0100 +0100'>August 15, 2024</span>&nbsp;·&nbsp;1 min&nbsp;·&nbsp;31 words&nbsp;·&nbsp;Damilola John

Descrambling Sentences with GPT2

Finetuning GPT2 to Reconstruct sentences Two words are anagrams if one can be formed by permuting the letters of the other. Applying the same logic to a sentence, would be saying that two sentences are anagrams(no such thing) if their component words can be permutated to form clones of each other. I thought it would be interesting to finetune a language model to do this. You might be thinking that simply re-arranging words in a sentence doesn’t require intelligence and can be done with very trivial algorithms,you would be right, but I added an edge to this task, given a random sequence of words, the language model has to return a grammatically correct sequence using the same set of words. For example, the following sequence: ...