Essentials for AI practitioners

Flow Judge: An Open Small Language Model for LLM System Evaluations

Read our in-depth technical report on Flow Judge, an open-source, small-scale (3.8B) language model optimized for efficient and customizable LLM system evaluations.

Self-Taught Evaluators Paper by Meta AI — Explained by AI Engineer

This research paper introduces a method to improve language model evaluators using only synthetic training data, which makes it extremely scalable and efficient.

MAGPIE Explained: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing

MAGPIE tackles two major pain points in current open data creation methods: making synthetic data generation scalable and reserving data diversity at scale.

Exploring the potential of open(-source) LLMs

We explore why companies initially opt for closed-source LLMs like GPT-4 and discuss the growing shift towards open LLMs.

From Data Analyst to AI Engineer (in 2024)

Discover Tiina's motivations, the skills she developed, and the challenges she faced while transitioning from data analytics consultant to an AI engineering role.

Improving LLM systems with A/B testing

By tying LLM performance to business metrics and leveraging real-world user feedback, A/B testing can help AI teams create more effective LLM systems.

Introduction to Model Merging

How can we make LLMs more versatile without extensive training? Model merging allows us to combine the strengths of multiple AI models into a single, more powerful model.

Prometheus 2 Explained: Open-Source Language Model Specialized in Evaluating Other Language Models

The Prometheus 2 paper introduces a new SOTA open LLM for evaluations that has high correlation with human evaluators and leading closed-source models.

LLM evaluation (2/2) — Harnessing LLMs for evaluating text generation

Evaluating LLM systems is a complex but essential task. By combining LLM-as-a-judge and human evaluation, AI teams can make it more reliable and scalable.

LLM evaluation (1/2) — Overcoming evaluation challenges in text generation

Evaluating LLM systems, particularly for text generation tasks, presents significant challenges due to the open-ended nature of outputs and the limitations of current evaluation methods.

Dataset Engineering for LLM Finetuning

Our lessons on fine-tuning LLMs and how we utilise dataset engineering.

Introduction to Prompt Engineering

What we learned about prompt engineering by building a SaaS product on top of LLMs.

Scaling SEO from 100K to 1M in 15 months (with 1-person marketing team)

They said early-stage startups should not go all-out on SEO. Well, we did anyways, and here’s what happened…

SEO content strategy that took us from 0 to 100k monthly visits in 6 months

Learn the SEO content strategy that focuses on solving customer pain points and spurred our growth to +25,000 signups.

How to launch on Product Hunt - what we learned?

Get our learnings on how to launch on Product Hunt and take a peek at our results to benchmark for your big day.

Dynamic table of contents on Webflow CMS – the easiest way

Step-by-step guide on how to automatically generate ToC's on Webflow with less than 10 lines of code and no plugins.

Flowrite's viral referral program – how we 8x'd our weekly signups

Step-by-step guide on how to build a low-code referral program to take your signups to the next level.