Talk2026
Talk· Speaker
Speaking at Conf42 Prompt Engineering 2026
Talk on keeping prompts stable as they change, using prompt contracts: structured outputs, explicit invariants, and automated tests.
Latest
All activity
The complete chronological feed across writing, projects, talks, and judging. Most recent first.
All entries
143 entries
- Talk2026Talk· Panelist
Speaking at SF Tech Week 2026
Trust Issues: When Agents Act for You
Panelist at Trust Issues: When Agents Act for You, on identity, access, and authorization for AI agents.
- Writing· Supervised learning · Chapter 3 of 50
Classification: predicting a category
Understand classification through labeled fruit pictures, new inputs, and a category recognition activity.
- Paper2026Paper· SPLASH 2026 · Tool Demonstrations
HeapLens at SPLASH 2026
An IDE-integrated tool for heap dump analysis with in-editor source bridging and LLM-assisted diagnosis
Tool paper on HeapLens in the companion proceedings of SPLASH 2026, the ACM SIGPLAN International Conference on Systems, Programming, Languages, and Applications.
- Writing· Supervised learning · Chapter 2 of 50
Regression: estimating an amount
Understand regression through known sale prices, a new home, and a simple price-gap experiment.
- Writing· Supervised learning · Chapter 1 of 50
Learning from examples
Understand model, learning, and prediction through completed deliveries, a playable example, and a numbered chapter infographic.
- Paper2026Paper· GroundLM 2026 at EMNLP
Evidence-Indexed Slide Narration
With heuristic checks and template fallback
Paper at the GroundLM 2026 workshop, co-located with EMNLP 2026, on keeping generated slide narration tied to what the slide actually contains.
- LLM Ops & Eval
- Paper2026Paper· GroundLM 2026 at EMNLP
Default Zero-Shot LLM APIs Over-Flag Indian Financial SMS
A policy-aligned benchmark and template-level pre-deployment audit
Paper at the GroundLM 2026 workshop, co-located with EMNLP 2026, on how often language-model APIs wrongly flag legitimate Indian financial text messages as fraud.
- LLM Ops & Eval
- Paper2026Paper· GroundLM 2026 at EMNLP
VERITYGATE
A four-gate schema-level faithfulness framework and paired benchmark for grounded LLM narrations over structured evidence
Paper at the GroundLM 2026 workshop, co-located with EMNLP 2026, on checking whether a model's written explanation actually follows the structured evidence it cites.
- LLM Ops & Eval
- Paper2026Paper· GroundLM 2026 at EMNLP
TRACE
Target-aware retrieval, attributed evidence, and contract-constrained extraction for LitTraceQA
Paper at the GroundLM 2026 workshop, co-located with EMNLP 2026, on the gap between finding the right paper and producing an answer a scorer can verify.
- RAG
- Search
