VBVikas Bhandaryinvikasbhandary.com.np·Dec 2, 2025 · 2 min readInstructGPT: fine-tuned GPT-3Large language models (LLMs) can frequently produce nonsensical, toxic, or made-up text that can easily fool typical users. These unintended behaviours stem from the inherent shortcomings of the language modelling objective: predicting the next token...00
VBVikas Bhandaryinvikasbhandary.com.np·Nov 30, 2025 · 3 min readInstruction tuning LLMsLarge language models (LLMs), which are artificial intelligence (AI) systems trained to process and generate human language, are trained on vast amounts of data from the internet. They learn about language and other complex linguistic concepts by opt...00
VBVikas Bhandaryinvikasbhandary.com.np·Nov 14, 2025 · 3 min readMT-Bench: LLM-as-a-judge benchmarkWith the rapid growth of research on large language models (LLMs), we now have a diverse array of models capable of performing various tasks. Current benchmarks for LLMs only focus on evaluating models on close-ended questions, with short responses. ...00
VBVikas Bhandaryinvikasbhandary.com.np·Jan 11, 2023 · 2 min readSave your development time by using AmplicationIf we talk about code generation tools, we can find many tools that won't require any domain expertise to go from an idea to a presentable website. We can try to use these tools to save some time, but most code generation tools take away the code ext...00