Skip to content
View K611-dot's full-sized avatar

Highlights

  • Pro

Block or report K611-dot

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse

Popular repositories Loading

  1. contamination-detector contamination-detector Public

    Toolkit for detecting benchmark/eval-data contamination in LLM training corpora

    Python

  2. quant-analyst-agent quant-analyst-agent Public

    Autonomous equity-research agent: a ticker in, a sourced investment memo out. Claude tool-use loop over SEC EDGAR + market data, schema-constrained synthesis, every claim cited.

    Python

  3. market-pulse market-pulse Public

    Watchlist market-event monitor: deterministic dedupe before any model call, materiality scoring against a cached rubric, ranked digest. Claude prompt caching + structured outputs.

    Python

  4. compsheet compsheet Public

    Trading comps from SEC XBRL filings. The model picks peers and writes commentary; every number in a cell is computed in Python. n/a and nm are different answers.

    Python

  5. rag-eval-harness rag-eval-harness Public

    RAG evaluation harness: deterministic retrieval metrics, an LLM judge that is itself scored against human labels, and a regression gate that tells a real drop from noise.

    Python

  6. promptfort promptfort Public

    Prompt-injection red-teaming harness for your own LLM app: canary-based deterministic breach detection, switchable guardrail layers, and a per-category before/after scorecard.

    Python