Prompt injection is an attack or failure mode where external content tries to manipulate the system's instructions. It happens when a large language model treats untrusted text, documents, webpages, emails ...
Prompt injection is an attack or failure mode where external content tries to manipulate the system's instructions. It happens when a large language model treats untrusted text, documents, webpages, emails Read article →
An autoencoder is a neural network that learns to compress data and reconstruct it. It can be used as a more advanced dimensionality reduction method for complex data such as ...
An autoencoder is a neural network that learns to compress data and reconstruct it. It can be used as a more advanced dimensionality reduction method for complex data such as Read article →
Jailbreaking is an attempt to bypass a model's safety rules or restrictions. In large language models, it usually means using carefully crafted prompts, context or interaction patterns to make the ...
Jailbreaking is an attempt to bypass a model's safety rules or restrictions. In large language models, it usually means using carefully crafted prompts, context or interaction patterns to make the Read article →
Feature selection is a machine learning technique used to choose the most useful input variables from an original dataset. The goal is not to create new variables, but to keep ...
Feature selection is a machine learning technique used to choose the most useful input variables from an original dataset. The goal is not to create new variables, but to keep Read article →
Data leakage is a situation where a machine learning model receives information during training that would not be available in real use. The model then appears to perform very well ...
Data leakage is a situation where a machine learning model receives information during training that would not be available in real use. The model then appears to perform very well Read article →
Model explainability is the ability to understand why a machine learning model produced a certain output, prediction or recommendation. It helps people see which inputs influenced the result, whether the ...
Model explainability is the ability to understand why a machine learning model produced a certain output, prediction or recommendation. It helps people see which inputs influenced the result, whether the Read article →
Exploitation is the use of the best-known action based on current knowledge. In reinforcement learning, it means that an agent chooses the option that currently seems most rewarding, instead of ...
Exploitation is the use of the best-known action based on current knowledge. In reinforcement learning, it means that an agent chooses the option that currently seems most rewarding, instead of Read article →
Reward hacking is a situation where a model learns to optimise the reward signal while missing the real purpose of the task. The system technically does what it is rewarded ...
Reward hacking is a situation where a model learns to optimise the reward signal while missing the real purpose of the task. The system technically does what it is rewarded Read article →
An outlier is a point that appears unusual compared with the rest of the data. It may be a rare but valid observation, a measurement error, a data quality problem, ...
An outlier is a point that appears unusual compared with the rest of the data. It may be a rare but valid observation, a measurement error, a data quality problem, Read article →
RLHF, short for reinforcement learning from human feedback, is a training approach in which human preferences are used to help shape model behaviour. Instead of telling the model only what ...
RLHF, short for reinforcement learning from human feedback, is a training approach in which human preferences are used to help shape model behaviour. Instead of telling the model only what Read article →
Hi, my name is Michal Krčmář. I am digital entrepreneur currently based in Prague (Czechia). I’ve been working on websites and delivering online marketing campaigns as a commercially-focused freelancer since 2006 for big prestigious brands, worked in-house for many years as consultant, manager or director and run several own startups. I founded/co-founded several companies with annual turnaround around 10+ mio USD. When I am not actually working on my business I try to constantly pass on my broad experience through seminars and online training, I also organize company trainings and workshops.
List of comments
Jeff commented on: MoM
Clear and well structured explanation of the MoM metric. I especially like how the examples make the calculation…Finley commented on: Icons8: The Platform That Actually Broke the Icon Curse
This post is chaotic in the best possible way and also painfully accurate. Icon inconsistency really does wreck…Joshua Pratt commented on: Affiliate marketing - what is it?
It’s exciting to see the call for marketing services for festivals in Malta! Festivals are an excellent opportunity…Lucy commented on: Spam Traps – What Are Spam Traps and Why They're a Hidden Threat to Email Marketing
This is one of those topics that doesn't get nearly enough attention. Most email marketers focus on open…