- Refusal Direction — Paper Critique
The one-dimensional refusal result is real. I just think the interpretation can be narrower than the title sounds.
- Role Confusion — Paper Critique
Prompt injection may be a source-authentication problem inside the model, not just bad instruction following.
- Alignment Faking — Paper Critique
A real existence proof for training-aware strategic behaviour, but not evidence that current models generally hide secret goals.
- AutoDAN — Paper Critique
Readable automated jailbreaks are the real contribution; the stealth and evaluation claims need narrower wording.
- RoPE
Mechanics-first explanation of Rotary Position Embeddings, 2D rotations, relative position, and long-context attention in Transformers.
- Neural Language Models Before Transformers
From bigram counts and Bengio's MLP to recurrent state, gated memory, and causal CNNs.
- Transformers From Scratch in Code
From tensor shapes and self-attention to a tiny GPT, RoPE, KV caching, and FlashAttention.
- Using-Pydantic-For-Structured-Outputs
Pydantic models for validated structured outputs, schema-constrained LLM responses, and typed tool calling in Python.
- AMR-Parsing-Summarization: A Graph-to-Text Framework
PyTorch AMR graph-to-text abstractive summarization from Abstract Meaning Representation graphs to neural text summaries.
- Cross-Modal Knowledge-Guided Summarization
BERT summarization guided by multimodal knowledge graphs in a paper-reproduction prototype.
Blog
Technical writing on LLM safety, AI agents, context engineering, transformers, deep learning, tool calling, and applied machine learning by Masih Moafi.