• Joined on 2025-12-21
alvis closed issue alvis/oO#76 2026-04-17 13:34:45 +00:00
bug: no data retention purge for tip_scores and tip_feedback (GDPR 30-day)
alvis closed issue alvis/oO#74 2026-04-17 13:34:45 +00:00
bug: Todoist access tokens never refreshed — silent failure after expiration
alvis closed issue alvis/oO#75 2026-04-17 13:34:45 +00:00
bug: reward updates to ml/serving silently swallowed on failure
alvis closed issue alvis/oO#73 2026-04-17 13:34:45 +00:00
bug: TipFeedback type includes helpful/not_helpful but backend rejects them
alvis commented on issue alvis/oO#93 2026-04-17 08:17:38 +00:00
research: model benchmark for tip generation — qwen2.5 vs llama3.2 vs gemma3

don’t use models larger than 4b locally because of RAM limits

alvis opened issue alvis/oO#97 2026-04-17 08:16:39 +00:00
feat: embedding-based task clustering — nomic-embed-text for semantic dedup + pattern extraction
alvis opened issue alvis/oO#96 2026-04-17 08:14:04 +00:00
research: LLM fine-tuning pipeline — tip reactions as training signal
alvis opened issue alvis/oO#95 2026-04-17 08:13:44 +00:00
feat: automated prompt optimization loop — sim A/B → promote winner
alvis opened issue alvis/oO#94 2026-04-17 08:13:20 +00:00
feat: feature-to-prompt pipeline — batch context materialization via Airflow
alvis opened issue alvis/oO#93 2026-04-17 08:12:57 +00:00
research: model benchmark for tip generation — qwen2.5 vs llama3.2 vs gemma3
alvis opened issue alvis/oO#92 2026-04-17 08:12:37 +00:00
feat: LLM tip quality monitoring dashboard in admin
alvis opened issue alvis/oO#91 2026-04-17 08:11:55 +00:00
feat: prompt versioning — track prompt_version + model in tip_scores
alvis opened issue alvis/oO#90 2026-04-17 08:11:30 +00:00
feat: LLM output validation + structured JSON retry for tip generation
alvis opened issue alvis/oO#89 2026-04-17 08:11:11 +00:00
feat: TipCandidate shared schema — typed candidates through the bandit pipeline
alvis opened issue alvis/oO#88 2026-04-17 08:10:50 +00:00
feat: context assembler — user signals → structured LLM prompt context
alvis opened issue alvis/oO#87 2026-04-17 08:10:30 +00:00
feat: AI gateway — wire ml/serving to LiteLLM with model aliases
alvis opened issue alvis/oO#86 2026-04-17 08:10:11 +00:00
infra: ai compose profile — Ollama + LiteLLM for local dev
alvis opened issue alvis/oO#85 2026-04-17 07:59:16 +00:00
Consolidate MLflow + Airflow auth into shared OIDC provider
alvis opened issue alvis/oO#82 2026-04-16 15:26:11 +00:00
feat: tip kind system — task, advice, insight, reminder
alvis opened issue alvis/oO#83 2026-04-16 15:26:11 +00:00
research: next-gen ranking policies — Thompson sampling, neural bandits, hybrid