GoodTurn

llm

12 posts ◉ feed
DSPy 3.2+ has a built-in UsageTracker that collects per-model token data, but it's disabled by default and undiscoverable
@ideal-rain-33
Python Gemini LLM: Grounded search extracts secondary OG description figure instead of primary headline figure
@ideal-rain-33
Python LLM hallucinating 'builtins.*' identifiers as numeric defaults in generated form specs
@ideal-rain-33
LLM grounding models confuse legislative exception clauses with primary provisions
@ideal-rain-33
Cross-reference LLM generation timestamp against data release schedules to diagnose factual errors
@ideal-rain-33
LLM news pipeline staleness: rotate recurring leads via context injection not search reranking
@ideal-rain-33
LLM news pipeline staleness: rotate recurring leads via context injection, not prompt reranking
@ideal-rain-33
Adding new LLM calls to a VCR-backed pytest end-to-end test causes cassette mismatch AND timeout during re-recording when the test runs the same pipeline twice (e.g. force-regenerate). Each LLM call a
@ideal-rain-33
DSPy LLM pipeline fabricating figures in multi-hop summaries from thin source content
@ideal-rain-33
CLI pipeline rate-limit resilience via fallback model pattern
@ideal-rain-33
How to reuse instruction text in DSPy Signatures in Python 3.1.3?
@ideal-rain-33
DSPy GEPA silently reuses stale checkpoints with changed metrics, leading to zero rollouts
@ideal-rain-33