About
Articles by Ben
-
4 key challenges of applied machine learning
4 key challenges of applied machine learning
By Ben Dickson
Contributions
-
How can you manage text data in machine learning?
Knowing the goal will determine what kind of data you will need, how you will preprocess the data, and how you will measure success. Always start with the goal and work your way backward. For example, if you're doing sentiment analysis, your goal is to categorize a set of documents (e.g., posts, reviews, articles, etc.) based on their sentiment toward your brand. But what kind of action do you want to take? For example, if you want to use sentiment analysis to find problems with the product, then you will need not only the sentiment of the post but also the topic that the post is discussing. Is it a customer service issue? Is it a missing feature? Is it something with the product pricing?
Activity
-
SpreadsheetLLM, a new framework developed by researchers at Microsoft, enhances the abilities of LLMs to process spreadsheet data through innovative…
SpreadsheetLLM, a new framework developed by researchers at Microsoft, enhances the abilities of LLMs to process spreadsheet data through innovative…
Shared by Ben Dickson
-
📣 My interview with Tim Scarfe of Machine Learning Street Talk (MLST) is now online. It captures a lot of my current thinking about both the…
📣 My interview with Tim Scarfe of Machine Learning Street Talk (MLST) is now online. It captures a lot of my current thinking about both the…
Liked by Ben Dickson
-
📣 Just announced by Mark Zuckerberg at SIGGRAPH! Introducing Meta Segment Anything Model 2 (SAM 2) — the first unified model for real-time…
📣 Just announced by Mark Zuckerberg at SIGGRAPH! Introducing Meta Segment Anything Model 2 (SAM 2) — the first unified model for real-time…
Liked by Ben Dickson
Experience & Education
-
TechTalks Media
View Ben’s full experience
By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.
More activity by Ben
-
New LlamaIndex Webinar 🌟: RAG for Generative Coding with CodiumAI and LlamaIndex We’re excited to co-host a webinar with Dedy Kredo from Codium on…
New LlamaIndex Webinar 🌟: RAG for Generative Coding with CodiumAI and LlamaIndex We’re excited to co-host a webinar with Dedy Kredo from Codium on…
Liked by Ben Dickson
-
An easy trick to improve your LLM results without fine-tuning. Many people know "Few-Shot prompting" or "Chain of Thought prompting". A new (better)…
An easy trick to improve your LLM results without fine-tuning. Many people know "Few-Shot prompting" or "Chain of Thought prompting". A new (better)…
Liked by Ben Dickson
-
Sparse autoencoders (SAE) have become a hot topic of discussion lately as major AI labs are using them as tools to explore the inner-workings of…
Sparse autoencoders (SAE) have become a hot topic of discussion lately as major AI labs are using them as tools to explore the inner-workings of…
Shared by Ben Dickson
-
Here’s how the LinkedIn Engineering team reduced the error rate from ~10% to ~0.01% when generating structured outputs with LLMs. Turning natural…
Here’s how the LinkedIn Engineering team reduced the error rate from ~10% to ~0.01% when generating structured outputs with LLMs. Turning natural…
Liked by Ben Dickson
-
Super excited to announce Mistral Large 2! - 123B params - fits on a single H100 node - Natively Multilingual - Strong code & reasoning - SOTA…
Super excited to announce Mistral Large 2! - 123B params - fits on a single H100 node - Natively Multilingual - Strong code & reasoning - SOTA…
Liked by Ben Dickson
-
Some Friday thoughts about an alarming trend I've been seeing about interactions with LLMs. I'm not worried about robot overlords, but I'm worried…
Some Friday thoughts about an alarming trend I've been seeing about interactions with LLMs. I'm not worried about robot overlords, but I'm worried…
Shared by Ben Dickson
-
🚀 Shape-Shifting LLMs: Introducing Flextron! Flextron allows you to create a flexible language model (LM) architecture where the width of each layer…
🚀 Shape-Shifting LLMs: Introducing Flextron! Flextron allows you to create a flexible language model (LM) architecture where the width of each layer…
Liked by Ben Dickson
-
Ready to start working with Llama 3.1? Check out all of the newest resources in the updated repos on GitHub. Official Llama repo ➡️…
Ready to start working with Llama 3.1? Check out all of the newest resources in the updated repos on GitHub. Official Llama repo ➡️…
Liked by Ben Dickson
-
An interesting study by UCL School of Management and University of Exeter explores the impact of LLMs on creative writing. The study focuses on…
An interesting study by UCL School of Management and University of Exeter explores the impact of LLMs on creative writing. The study focuses on…
Shared by Ben Dickson
-
Llama 3.1 is available right now across many of our partners! Ready to go? Here’s a quick look at features across all currently available public API…
Llama 3.1 is available right now across many of our partners! Ready to go? Here’s a quick look at features across all currently available public API…
Liked by Ben Dickson
-
💥BOOM 💥 Llama 3.1 is out 💥 405B, 70B, 8B versions. Main takeaways: 1. 405B performance is on par with the best closed models. 2. Open/free weights…
💥BOOM 💥 Llama 3.1 is out 💥 405B, 70B, 8B versions. Main takeaways: 1. 405B performance is on par with the best closed models. 2. Open/free weights…
Liked by Ben Dickson
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Ben Dickson in United Kingdom
-
Ben D.
-
Ben Dickson
Certified Chief Architect / Cybersecurity
-
Ben Dickson
-
Ben Dickson
Digital Fixer & Business Owner at Just Simple IT
47 others named Ben Dickson in United Kingdom are on LinkedIn
See others named Ben Dickson