LLM vs LRM vs LDM
A concise guide to three model families shaping language, reasoning, and generation.
·
2 min read
Eight Mile · Writing
Engineering notes, write-ups and the occasional opinion.
A concise guide to three model families shaping language, reasoning, and generation.
·
2 min read
Combine rule-based detection with lightweight NER for safer, practical sensitive-data masking.
·
4 min read
Using pgvector for embeddings without adding another database, covering index choice, filtering, quantisation and the point at which you should move off it.
·
9 min read
A practical tour of how OpenSearch stores and scores documents, where teams usually go wrong with mappings and shards, and what it costs to run.
·
9 min read
How similarity search works under the hood, what the index types trade against each other, and how to choose a store without over engineering the problem.
·
9 min read
The threats specific to language model applications, why prompt injection has no clean fix, and the architectural decisions that actually contain the damage.
·
9 min read
What each library actually does, where the split between them lies, when a framework earns its place in your stack, and when plain code is the better answer.
·
6 min read
What it takes to run a language model feature in production: evaluation, versioning, cost control, observability, and the failures monitoring never catches.
·
7 min read
Retrieval augmented generation explained properly: what happens at each stage, why the retrieval half is where projects succeed or fail, and how to evaluate it.
·
8 min read
The exact steps we used to scale fast using Checkatrade, AI, and a quoting system that closed deals like clockwork.
·
8 min read
Close more deals with streamlined tools that drive smarter, faster sales.
·
1 min read
Generate quotes faster with intelligent automation that saves time and boosts conversions.
·
1 min read