styxx good first issues (Python)

Replicate: the mutual-legibility matrix (CPU-only, no GPU, committed data) 19 days ago

good first issue help wanted reproducible-research

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 collateral census (public corpus, CPU-only, deterministic) 19 days 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

Re-adjudicate our failure: 130 sealed items, our answers are already committed 19 days 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

Open problem: a direction-sensitive cross-model discovery method 20 days 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

OATH verifier: close the trigger-recall gap (52% of decimals sit on unbound lines) 20 days 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

observe() should warn the first time it's called without logprobs enabled 5 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 5 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 5 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

fathom-lab/styxx

Open Issues Need Help