Ines Montani

Agentic coding assistants have transformed the way we build software – and they can be even more impactful for AI development itself. So what if we could take some of the learnings from AI-powered coding assistants and apply them to building our own custom AI systems that are better, faster and fully under our control?

Agentic coding assistants have transformed the way we build software – and they can be even more impactful for AI development itself. Instead of using LLM APIs, we can take back control and build our own AI systems, bootstrapped for us by agents.

One of the hardest parts of applied NLP has always been breaking down complex business problems into machine learning components. It's so hard because it requires domain expertise and reasoning about the specific use case, and it's the one thing technology couldn't fix.

One of the hardest parts of applied NLP has always been breaking down complex business problems into machine learning components. It's so hard because it requires domain expertise and reasoning about the specific use case, and it's the one thing technology couldn't fix.

From developer workflows to corporate strategy to carbon footprints — AI is changing everything. Join us for this panel discussion to unpack its wide-reaching impacts and explore how we can steer this powerful technology toward better outcomes.

NLP and data science could be so easy if all of our data came as clean and plain text. But in practice, a lot of it is hidden away in PDFs, Word documents, scans and other formats that have been a nightmare to work with.

This fireside chat brings together leading voices from industry and open-source to explore how artificial intelligence is being meaningfully integrated into enterprise environments—beyond the buzzwords.

NLP and data science could be so easy if all of our data came as clean and plain text. But in practice, a lot of it is hidden away in PDFs, Word documents, scans and other formats that have been a nightmare to work with.

Large Language Models (LLMs) and in-context learning have introduced a new paradigm for developing natural language understanding systems: prompts are all you need! Prototyping has never been easier, but not all prototypes give a smooth path to production.

As the field of natural language processing advances and new ideas develop, we’re seeing more and more ways to use compute efficiently, producing AI systems that are cheaper to run and easier to control.

With the latest advancements in NLP and LLMs, and big companies like OpenAI dominating the space, many people wonder: Are we heading further into a black box era with larger and larger models, obscured behind APIs controlled by big tech? I don’t think so, and in this talk, I’ll show you why.

With the latest advancements in Natural Language Processing and Large Language Models (LLMs), and big companies like OpenAI dominating the space, many people wonder: Are we heading further into a black box era with larger and larger models, obscured behind APIs controlled by big tech monopolies?

With the latest advancements in Natural Language Processing and Large Language Models (LLMs), and big companies like OpenAI dominating the space, many people wonder: Are we heading further into a black box era with larger and larger models, obscured behind APIs controlled by big t

With the latest advancements in Natural Language Processing and Large Language Models (LLMs), and big companies like OpenAI dominating the space, many people wonder: Are we heading further into a black box era with larger and larger models, obscured behind APIs controlled by big tech monopolies?...

Large Language Models (LLMs) offer a lot of value for modern NLP and can typically achieve surprisingly good accuracy on predictive NLP tasks with a reasonably structured prompt and pretty much no labelled examples.

In this talk, I'll show how large language models such as GPT-3 complement rather than replace existing machine learning workflows. Initial annotations are gathered from the OpenAI API via zero- or few-shot learning, and then corrected by a human decision maker using an annotation tool.