Three Types of Transformers
Encoder, decoder, and seq2seq transformers compared by what they output, an example model, typical use cases, and typical size.
I build AI applications with a systems mindset and use this site to share projects, technical notes, and visual sketches on applied AI, backend systems, and cloud infrastructure.
Recent Posts
Encoder, decoder, and seq2seq transformers compared by what they output, an example model, typical use cases, and typical size.
Notes on the three transformer architectures, chat templates and special tokens, tool calling and MCP, and the agent Thought/Action/Observation loop.
Requirements, short code generation strategies, caching, and scaling reads and writes with separate read/write services.
A pipeline that turns raw video into scene-segmented, cross-checked, precisely-timed audio descriptions.
A short note on PPO and DPO, two ways to align a model's responses with human preferences.
Contact