OpenAI
LLM training and post-training. Expect transformer internals, attention variants, sampling, and tokenization.
58 problems tagged for OpenAI.
Sign in to track your progress0%
Solve a problem (pass its tests) and it's checked off here automatically — your progress is saved, so it stays checked when you come back.
- Adam optimiser stepMedium
- BERTScore (Greedy Token-Cosine F1)Medium
- Best-of-N SelectionEasy
- Bradley-Terry Strength MLEHard
- Scaled dot-product self-attentionMedium
- Citation Attribution AssemblyMedium
- CLIP InfoNCE LossMedium
- Constrained Decoding Logit MaskMedium
- Continuous Batching SchedulerHard
- Critic Verdict ParserEasy
- Cross-Attention (Encoder-Decoder)Medium
- Cross-Encoder Rerank Top-kEasy
- DDPM Reverse (Denoise) StepMedium
- Elo Rating UpdateEasy
- Expected Calibration Error (ECE)Medium
- Exponential Backoff + JitterEasy
- Faithfulness / Groundedness ScoreMedium
- Generalised Advantage Estimation (GAE)Medium
- IPO / SimPO LossMedium
- JSON Tool-Arg RepairMedium
- Kendall's TauMedium
- KTO (Kahneman-Tversky) LossHard
- KV-Cache Eviction (Sliding Window)Medium
- Little's LawEasy
- Sentence Embedding (Masked Mean-Pool)Easy
- Matryoshka Embedding TruncationMedium
- Multi-Query Fan-Out + DedupEasy
- Multi-Tool Router (by Embedding)Medium
- ORPO Loss (Odds-Ratio Preference Optimisation)Medium
- Paged-Attention KV Block AllocationMedium
- Parent-Document RetrievalMedium
- pass@k Unbiased EstimatorMedium
- Plan-DAG Cycle DetectionMedium
- Planner Output ParserEasy
- Prefix-Cache Hit AccountingEasy
- Prompt-Injection HeuristicMedium
- QA Token F1 / Exact MatchMedium
- ReAct Loop DriverMedium
- Recall@k (Retrieval)Easy
- Reciprocal Rank Fusion (RRF)Medium
- Recursive Chunking with OverlapMedium
- Reflexion Retry With FeedbackMedium
- Refusal / Confidence GateEasy
- Reward-Model Margin LossMedium
- Risk-Coverage Curve (AURC)Medium
- Run-Level Cost / Budget CeilingMedium
- Self-Consistency Majority VoteEasy
- Semaphore-Bounded Concurrent TasksMedium
- Shared-Memory Tool-Call CacheMedium
- Spearman Rank CorrelationEasy
- Streaming SSE Delta AssemblerEasy
- Stop-Sequence Detection (Streaming)Easy
- Task-DAG Parallel SchedulerHard
- Token-Bucket Rate LimiterEasy
- Token-Budget Context ManagerMedium
- Tool-Call Parse + Schema ValidationMedium
- Trace Aggregation SummaryEasy
- ViT Patch EmbeddingMedium