Building an automated Evals workflow that works (and open-sourcing it)
How we built Kaleidoscope: A structured workflow for realistic, scalable, and human-aligned contextual AI evaluations.
Responsible AI
A collection of 11 posts
Yes, you’re absolutely right… Right? A mini survey on LLM sycophancy
Ever spoken to an AI and felt like it was responding with insincere praise?
Benchmarking GPT-5 & GPT-OSS: A Responsible AI Approach
Evaluating dimensions often overlooked by traditional benchmarks.
Introducing LionGuard 2: Multilingual LLM Guardrail for Singapore
We improved its coverage and robustness.
RabakBench: Multilingual AI Safety Evaluation Made Local
Global safety guardrails are often blind to local dialects and sensitivities.
Does your LLM know when to say “I don’t know”?
Refusal by a model to answer may sometimes be more valuable.
Fine-Tuning Language Models for Long-Context Data: Automated Stance Analysis of Citizen Discussions
Addressing technical challenges of processing high-volume public feedback for policy-making
Securing Guardrails with Automated Red Teaming
Manual testing is no longer scalable.
(Part 2) LLM Safety Alignment for the Singapore Context using Supervised Fine-tuning and RLHF-based Methods
Safety must be "baked in".
(Part 1) LLM Safety Alignment for the Singapore Context using Supervised Fine-tuning and RLHF-based Methods
The process of "teaching" models to be safe
Eliciting Toxic Singlish from r1
A red-teaming exercise that proves even "reasoning" models can be coaxed.