Day 4 · Thu 2026-10-08 · ChatGPT CORE

ChatGPT CORE serving: streaming, reconnect, scheduling, quotas, and context cost

Week 11 trains two designs with one operating spine: admission, isolation, durable work, queue/backpressure, streaming/reconnect, derived state, evals, and recovery.

3contiguous 1-D DP slots
25-35mattempt + follow-up window
Staffinvariant, failure, recovery, metrics

Exact Daily Schedule

No drift: the same six blocks run every day.

TimeBlockContract
08:50-09:00TargetWrite one Staff-level invariant and one failure window before reading.
09:00-10:05Project design25-35m ChatGPT serving follow-up, then streaming/scheduler/quota/context deep dives.
10:05-10:45DDIA / source groundingMap the design to exact DDIA anchors and only direct applied-AI sources.
10:45-10:55Spoken closeRecord the architecture in English, then say the Chinese invariant aloud.
14:30-16:151-D DP contiguous blockThree NeetCode slots below; each slot is 25-35 minutes plus follow-up.
20:30-21:15Recall / artifactRun English Senior+/Staff recall and patch the scorecard evidence.

Canonical Hello Interview Anchors

Direct day-page anchors only. Source titles were verified live before build.

Canonical anchorDispositionDesign decision
Potential Deep DivesCORE deep diveDeep dives must connect user-visible UX to serving constraints.
How do we stream tokens back fast and keep the stream smooth?CORE deep diveSSE cursor, replay buffer, heartbeats, and reconnect semantics.
How do we route and schedule generation requests across GPU workers?CORE deep diveScheduler accounts for model, prompt length, tier, queue age, and GPU capacity.
How do we keep heavy users from monopolizing GPUs while giving paid tiers a better experience?CORE deep diveQuota, token buckets, queue lanes, and paid-tier fairness.
As conversations get longer, how do we control inference cost without making the assistant feel forgetful?CORE deep diveContext selection, summarization, retrieval, and prompt cache economics.
Cancelling a run and reclaiming the GPUCORE deep diveCancellation is a run-state transition plus worker cleanup.

Exact DDIA Mapping

Only Ch5, Ch9, and Ch13 sections are in scope.

ChapterExact sectionInterview use
Ch5持久化执行Long model calls persist inputs, state, retries, and cancellation.
Ch5消息代理Token events and status changes need replayable fanout for reconnect.
Ch9超时和无界延迟GPU queues need explicit overload modes and tier fairness.

Applied AI Source Gate

First-party/original sources appear only when they change a serving, eval, security, or operating decision.

First-party/original sourceConcrete decision it changes
OpenAI - Streaming API responsesUse event streams, cursors, and retryable UI behavior rather than treating the response as one blocking blob.
OpenAI - Background modeLong-running generation or tool calls become durable background runs with polling or reconnect.
OpenAI - Prompt cachingContext-pack ordering and stable prefixes become serving and cost decisions.
OpenAI - Rate limitsAdmission control must account for requests, tokens, tiers, and ingestion limits.

21-Slot 1-D DP Runway

Today is slot 10-12 of 21, contiguous across the week.

BlockNeetCode problemModeInvariant25-35m follow-upComplexity
14:30-15:05Word BreakPrefix feasibilitydp[i] is true if any previous valid split plus dictionary word reaches i.Ask for trie or max-word-length optimization.O(n^2) / O(n)
15:05-15:40Longest Increasing SubsequencePatience tailstails[k] is the smallest possible tail for length k+1.Ask for O(n^2) DP proof and O(n log n) upgrade.O(n log n) / O(n)
15:40-16:15Partition Equal Subset Sum0/1 subsetReverse iterate sums so each number is used once.Ask why forward iteration corrupts 0/1 semantics.O(n * target) / O(target)

Artifacts And Recall

Use these in the evening block and scorecard.

Required spoken close: explain one invariant, one failure window, one recovery path, and one metric in English. Then restate the same design decision in Chinese without adding new components.
Local study materials
Detailed lecture notes, audio, recall scripts, PDFs, Staff Q&A, and mock packs are archived locally and are intentionally not published on this site.