6 June 2023
Writing
Writing about open language models
Wrote about open models like Falcon, which can be adapted and run outside a single vendor’s service.
Notes & links
From a public post. Public post ↗ · Link to this entry
Skill
Model evaluation
6 entries mention it. All skills →
19 March 2024
Experiment
Synthetic data, fine-tuning and quantization loops
Tried a loop where a model helps write and clean up training data for one task, then gets fine-tuned and quantized, and the cycle repeats.
Synthetic data, Fine-tuning, Quantization, Model evaluation
Notes & links
From a public post. Public discussion ↗ · Link to this entry
30 April 2024
Writing
Models and serialized data
Asked how models behave when given serialized or binary data, and what security risks that opens.
Serialization security, Model evaluation
Notes & links
From a public post. Public post ↗ · Link to this entry
June–October 2025
Writing
Writing about capability and agent risk
Wrote about the security risks that come with more capable models and agents, and the trade-offs of using smaller, task-specific models.
Agent security, Risk analysis, Model evaluation
Notes & links
March 2026
Research
Testing what model adaptation preserves and changes
Shared what I saw inside models after fine-tuning, and suggested checking whether it holds for other model families.
Activation analysis, Model evaluation, Cross-model evaluation, Fine-tuning
Notes & links
From a public post. Public discussion ↗ · Link to this entry
12 April 2026
Research
Latent Contextual Reinforcement
Wrote up a research idea about guiding small models to reason better without retraining all of their weights.
Reasoning-model training, Expert scaffolding, Model evaluation
Notes & links
From a public post. Public post ↗ · Link to this entry