Remove Examples Remove Software Engineering Remove System Design
article thumbnail

The software engineering rule of 3

Erik Bernhardsson

Here’s a dumb extremely accurate rule I’m postulating* for software engineering projects: you need at least 3 examples before you solve the right problem. Example plz. The same reasoning applies to system design but with a very different conclusion. Wait until you have at least three.

article thumbnail

The road to Software 2.0

O'Reilly Media - Data

Instead, we can program by example. We can collect many examples of what we want the program to do and what not to do (examples of correct and incorrect behavior), label them appropriately, and train a model to perform correctly on new inputs. In short, we can use machine learning to automate software development itself.

Software 338
article thumbnail

The software engineering rule of 3

Erik Bernhardsson

Here’s a dumb extremely accurate rule I’m postulating* for software engineering projects: you need at least 3 examples before you solve the right problem. Example plz. The same reasoning applies to system design but with a very different conclusion. Wait until you have at least three.

article thumbnail

Making Apache Kafka Serveless: Lessons From Confluent Cloud

Confluent

Serverless offerings in the cloud are a favorite among software engineers—a prime example are object stores such as AWS S3. For the system designer, however, it is an engineering challenge […].

Cloud 105
article thumbnail

What LinkedIn learned leveraging LLMs for its billion users

CIO

For LinkedIn, this was no different, as its road to LLM insights was anything but smooth, said LinkedIn’s Juan Bottaro, a principal software engineer and tech lead. For example, an early version of the revised job-matching effort was rather, for the lack of a better word, rude. Not enough dots were being connected.”

article thumbnail

Accelerating insurance policy reviews with generative AI: Verisk’s Mozart companion

AWS Machine Learning - AI

The following screenshot shows an example of the output of the Mozart companion displaying the summary of changes between two legal documents, the excerpt from the original document version, the updated excerpt in the new document version, and the tracked changes represented with redlines.

article thumbnail

Ground truth generation and review best practices for evaluating generative AI question-answering with FMEval

AWS Machine Learning - AI

For example, if ground truth is generated by LLMs before the involvement of SMEs, SMEs will still be needed to identify which questions are fundamental to the business and then align the ground truth with business value as part of a human-in-the-loop process. For our example, we work with Anthropics Claude LLM on Amazon Bedrock.