Jacek Fleszar

Some folks believe that training open-source LLMs is a losing battle and a complete waste of time. They argue that the gap between closed models like GPT-4 and open models like Llama will widen and these. Yes, closed models like Google’s Gemini or Open AI’s Gobi promise to be way more powerful than GPT-4, so what hope does open source...

The Turing test was developed by Alan Turing(A computer scientist) in 1950. He proposed that the “Turing test is used to determine whether or not a computer(machine) can think intelligently like humans”? The basic idea of the Turing Test is simple: a human judge engages in a text-based conversation with both a human and a machine, and then decides which of the two they believe to be a human. If...

https://medium.com/@fleszarjacek/agents-in-artificial-intelligence-3c68177cfa60

In summary, AI is still extremely early when it comes to reasoning and we may need a another significant breakthrough before LLMs can really measure up to humans.👈 https://medium.com/@fleszarjacek/why-large-language-models-hallucinate-and-how-to-reduce-it-1003c4a7c6f3

LLMs (Large Language Models) show powerful capabilities, but not knowing how to effectively and efficiently use them often leads to unexpected behaviors. Prompt engineering helps to reduce failure cases and computing costs when building with LLMs.👈 https://medium.com/@fleszarjacek/llms-and-sql-7cc74738424a

LLMs (Large Language Models) show powerful capabilities, but not knowing how to effectively and efficiently use them often leads to unexpected behaviors. https://maven.com/dair-ai/prompt-engineering-llms

https://api.daily.dev/devcards/ccd24fe9b4984089b865f3f75116528b.png?r=lga

We used to compare Llama 2 7b, 13b and 70b (chat-hf fine-tuned) vs OpenAI gpt-3.5-turbo and gpt-4. We used a 3-way verified hand-labeled set of 373 news report statements and presented one correct and one incorrect summary of each. Each LLM had to decide which statement was the factually correct summary.🧐 https://link.medium.com/QGud6Kn0xCb

Microservices are a type of service-oriented architecture that is used to develop multifunctional and complex applications. Instead of creating a complete software unit, developers can add small services to create software.👈 https://link.medium.com/eBEqds5ZuCb

LangChain is a framework for developing applications powered by language models. It enables applications that are: https://link.medium.com/onC3rwmitCb

Interact privately with your documents using the power of GPT, 100% privately, no data leaks. Built with LangChain, GPT4All, LlamaCpp, Chroma and SentenceTransformers.💐 https://link.medium.com/rQkxr7edqCb

Datasette Cloud is now a significant step closer to general availability. The Datasette 1.03 alpha release is out, with a mostly finalized JSON format for 1.0. Plus new plugins for LLM and sqlite-utils 👈