Research / writing

Questions worth making legible.

Academic papers and public writing on explainability, generative systems, model behavior, and the practical work of evaluating AI security systems.

01 / Academic writing

Research, in full.

Independent papers on explainable AI and generative media.

01March 2026Independent paper

Towards Transparent Reasoning

A survey of explainable AI methods, including LIME, SHAP, integrated gradients, and emerging reasoning-chain approaches for exposing model behavior.

Topic · Explainable AI
02March 2026Independent paper

The Diffusion Revolution

A review of the evolution from GANs to diffusion-based systems, covering DALL-E, Stable Diffusion, Sora, and open-source generative video work.

Topic · Generative media

02 / Blog writing

Notes from the field.

Public writing from my work at Semgrep, focused on AI code security and model evaluation.

01August 2026Semgrep blog

Semgrep Multimodal Goes Beyond Authentication: What we learned from Comparing it with Mythos

A comparison of Semgrep Multimodal and Mythos on 275 manually reviewed IDOR labels, showing how combining program analysis with AI reasoning improves coverage of authorization bugs.

Topic · AI code security
02August 2026Semgrep blog

We benchmarked A LOT of models, here’s how they compare to Mythos

A benchmark of Mythos against 22 model and harness configurations on 275 human-reviewed IDOR labels, with a closer look at precision, recall, and the effect of security harnesses.

Topic · Benchmarking
03August 2026Semgrep blog

GLM 5.3 Delivers Opus 4.8-Level Cybersecurity Results at a Fraction of the Cost

An evaluation of GLM 5.3's cybersecurity performance against Claude Opus 4.8, highlighting frontier-level results at a much lower cost.

Topic · AI code security
04July 2026Semgrep blog

Kimi K3's Code Security Results Look Competitive — Until You Look at Precision

A benchmark review of Kimi K3 that looks past headline F1 scores at precision, recall, and performance on larger codebases.

Topic · AI code security
05July 2026Semgrep blog

Grounded or Gamed? We Audited Our Own Cyber Benchmark

An audit of whether cyber-benchmark scores reflect grounded reasoning or shortcuts, with a focus on stability and counterfactual behavior.

Topic · Benchmarking
06July 2026Semgrep blog

Evaluating GPT-5.6 Luna, Terra, and Sol Against GPT-5.5 for AI Code Security

A model comparison through the lens of AI-powered vulnerability detection, including precision, recall, F1, and cost per true positive.

Topic · AI code security
07June 2026Semgrep blog

We Have Mythos at Home: GLM 5.2 Beats Claude in Our Cyber Benchmarks

A benchmark of GLM-5.2 against frontier models for IDOR detection, separating bare-model performance from the effect of a security harness.

Topic · Benchmarking