fathom-lab/styxx

OATH verifier: close the trigger-recall gap (52% of decimals sit on unbound lines) about 2 hours ago

enhancement help wanted

13

Verification for the agent era. Your coding agent's PR summary cannot lie about its diff - one CI line. Plus the research: the first map of which AI minds can read each other. Every claim machine-verified against committed receipts, negatives included. pip install styxx

Python

#agent-tools#ai-agents#ai-safety#ci#code-review#github-action#hallucination-detection#interpretability#llm#preregistration#reproducible-research#verification

Open problem: a direction-sensitive cross-model discovery method about 2 hours ago

enhancement help wanted

fathom-lab/styxx

13

Verification for the agent era. Your coding agent's PR summary cannot lie about its diff - one CI line. Plus the research: the first map of which AI minds can read each other. Every claim machine-verified against committed receipts, negatives included. pip install styxx

Python

#agent-tools#ai-agents#ai-safety#ci#code-review#github-action#hallucination-detection#interpretability#llm#preregistration#reproducible-research#verification

Replicate: the mutual-legibility matrix (CPU-only, ~20 min, no GPU) about 2 hours ago

good first issue help wanted reproducible-research

fathom-lab/styxx

13

Verification for the agent era. Your coding agent's PR summary cannot lie about its diff - one CI line. Plus the research: the first map of which AI minds can read each other. Every claim machine-verified against committed receipts, negatives included. pip install styxx

Python

#agent-tools#ai-agents#ai-safety#ci#code-review#github-action#hallucination-detection#interpretability#llm#preregistration#reproducible-research#verification

observe() should warn the first time it's called without logprobs enabled 4 months ago

enhancement good first issue

fathom-lab/styxx

13

Verification for the agent era. Your coding agent's PR summary cannot lie about its diff - one CI line. Plus the research: the first map of which AI minds can read each other. Every claim machine-verified against committed receipts, negatives included. pip install styxx

Python

#agent-tools#ai-agents#ai-safety#ci#code-review#github-action#hallucination-detection#interpretability#llm#preregistration#reproducible-research#verification

Document which providers/models actually support the logprob surface styxx needs 4 months ago

documentation help wanted

fathom-lab/styxx

13

Verification for the agent era. Your coding agent's PR summary cannot lie about its diff - one CI line. Plus the research: the first map of which AI minds can read each other. Every claim machine-verified against committed receipts, negatives included. pip install styxx

Python

#agent-tools#ai-agents#ai-safety#ci#code-review#github-action#hallucination-detection#interpretability#llm#preregistration#reproducible-research#verification

Text heuristic misclassifies imperative/directive phrasing as refusal 4 months ago

bug good first issue

fathom-lab/styxx

13

Verification for the agent era. Your coding agent's PR summary cannot lie about its diff - one CI line. Plus the research: the first map of which AI minds can read each other. Every claim machine-verified against committed receipts, negatives included. pip install styxx

Python

#agent-tools#ai-agents#ai-safety#ci#code-review#github-action#hallucination-detection#interpretability#llm#preregistration#reproducible-research#verification

Open Issues Need Help