ds-forge

Jun 17, 2026 · 1 min

The owner kept hitting basic frontend terms (toast, banner) and not knowing them. The deck had React fundamentals but no everyday UI-pattern vocabulary, so added 26 verified cards with TS/React/CSS code (not Java).

Jun 16, 2026 · 1 min

The monthly Claude limit that blocked the verify pass reset, so re-ran a verify-only pass over the 32 held technical cards (all passed) and shipped them. 81 of the 89 should/nice cards are now live and fact-verified; the 8 personal-narrative ones stay held.

Jun 16, 2026 · 1 min

Generated 89 cards for the remaining should/nice coverage gaps, but the monthly API spend limit was hit partway through the fact-verify pass. Shipped only the 49 that passed verification; the 40 unverified (incl. 8 personal-narrative cards) are held rather than shipped unchecked.

Jun 15, 2026 · 1 min

The owner's real goal for the per-card ask-AI box was to record the discussion, not just get one answer — for each topic he keeps hitting things he doesn't know and wants the whole back-and-forth saved. AskCard now persists its Q&A per card to localStorage, so it survives closing the modal and reloads.

Jun 15, 2026 · 1 min

The owner wanted to ask and hear the per-card AI by voice — an actual conversation, not typing — and wanted it on system design and phrases too. AskCard now records by mic, transcribes, asks, and speaks the answer back, with the persisted history intact, and it now lives on concepts, AI, system design, LLD, and phrases.

Jun 15, 2026 · 2 min

The standing rule is that every Korean study field needs an English twin. The Move Decks' trade-offs and applies-to notes and the behavioral STAR breakdowns were still Korean-only, so translated all 452 strings and rendered both languages.

Jun 15, 2026 · 1 min

The owner's standing rule is that every Korean field needs an English twin. The code walkthrough was Korean-only, so generated an English version 1:1 for all 202 cards and rendered both. A field-by-field sweep then surfaced the remaining Korean-only content to fix next.

Jun 15, 2026 · 2 min

The owner is prepping for an interview trusting only this deck, and asking concurrency terms surfaced that a lot was missing. Rather than patch ad hoc, ran a 9-domain coverage audit (canonical interview topics vs the real deck inventory) to make every gap visible, then started filling the MUST gaps — concurrency first (20 cards).

Jun 15, 2026 · 1 min

Continued filling the coverage-audit MUST gaps: 31 more /concepts cards (JVM internals, MVCC, system-design estimation/scaling, DSA, distributed-systems depth, LLD patterns) and the one genuinely-missing AI card (vector indexing). 52 cards added total across the three batches.

Jun 15, 2026 · 2 min

Closed the final 7 MUST-level coverage gaps across three decks (concepts, phrases, dbperf). Routed the trust-battery / no-surprises gaps to phrase cards (how to articulate them) instead of inventing behavioral STAR stories. MUST coverage is now complete; only should/nice depth remains.

Jun 15, 2026 · 1 min

Upgraded the two adversarial features (sparring, ai-audit) from gpt-4o to gpt-5. The first deploy 502'd with 'unparseable model response' because gpt-5 spent the entire token budget on hidden reasoning; fixed by raising max_completion_tokens and setting reasoning_effort low.

Jun 14, 2026 · 1 min

After I'd called the study content done before it was verified, the owner stopped trusting the static text outright. Rather than ask him to trust the next round of fixes, added a per-card 'ask AI' box that sends the card's own content as grounding so he can fact-check, clarify, or get examples live — and it's told to flag the card if it's wrong, not defend it.

Jun 14, 2026 · 1 min

The concept and AI cards showed self-attack questions with no model answer, and code with thin comments. Added a senior model answer plus a Korean 'why' for every probe (revealed on tap so you try first), and a function-by-function Korean walkthrough of every code snippet — so each card is an hour-long lesson. The verify stage was rate-limited, so the content shipped generate-only with that flagged.

Jun 14, 2026 · 1 min

After repeatedly claiming the study content was done when it wasn't fully verified, ran a pass where 41 agents each read cards from the actual source and fact-checked code, code explanations, English, and model answers. It corrected 23 more cards on top of an earlier 22 — 45 real errors across 202, about a fifth of the deck.

Jun 14, 2026 · 1 min

The deep-study layer shipped generate-only because the verify stage was rate-limited. Re-running the fact-check found 22 model answers across 21 cards that were technically wrong — about 3.5% of the generated answers — and corrected them, so the answers are now verified, not just generated.

Jun 13, 2026 · 2 min

Owner asked how many words he needs to speak actively and for a vocabulary list. The honest answer: functional fluency is ~2,000–3,000 active word families he mostly already knows passively — the real gap is active retrieval under pressure and the connective tissue that keeps speech flowing. Added 140 native-verified high-leverage cards (connectors, hedges, flexible/ownership verbs, engineering collocations) instead of a rare-word list.

Jun 13, 2026 · 2 min

The owner's root anxiety is not being able to tell whether AI output is right — which is exactly the JD's default-to-AI grade. Built a voice mode that inverts the spar: the AI proposes a system design or code with planted flaws, and you audit it out loud (restate, flag the risk, ask a clarifying question); it scores understanding and catching, then teaches what you missed.

Jun 13, 2026 · 3 min

Codex added ~14k lines of interview-drill content in one commit. A prior Gemini review covered architecture and security but explicitly skipped per-drill content. A content-accuracy audit (review then independent adversarial confirm) found 4 real factual errors in the memorize-and-say material — including an inverted p99 definition and a coin-change DP snippet that crashes.

Jun 13, 2026 · 1 min

The owner asked what 'corpus' is, then 'why did you leave it out?' He was right — the jargon deck had been scoped to infra/process/git and skipped data and AI-infra terms entirely. Added 36 native-verified cards for that category.

Jun 13, 2026 · 1 min

The owner is here to study real English, and Concept Atlas + AI Camp had several study fields in Korean only — the subtitle, the self-attack probes, and the failure modes. The main explanation already had English (rawEn/explainEn), but these did not. Added real-workplace-English versions for all 202 cards and render them alongside the Korean.

Jun 13, 2026 · 1 min

Added 84 everyday and workplace English phrase cards to /phrases across 12 real-life situations. After this session's audits caught errors in raw-generated content, every card went through a second independent native-correctness pass that rewrites or rejects textbook phrasing before it ships.

Jun 13, 2026 · 2 min

The Concept Atlas and AI Camp code fields averaged 2.9 lines — sketches, not something you could learn the mechanism from. A generate-then-verify workflow rewrote all 202 into complete worked examples (avg 27 lines), each independently correctness-checked, then integrated with html.unescape and template-literal escaping.

Jun 13, 2026 · 2 min

The owner kept hitting workplace and infra jargon he'd never heard — sidecar, canary, dark launch, toil, bikeshedding — and felt lost. Generated and native-verified 76 high-frequency jargon cards, each with the meaning, a real sentence using it, and the common misuse to avoid, and routed the long tail to the on-demand term finder.

Jun 13, 2026 · 2 min

Concept Atlas, AI Camp, and Phrases were grouped by domain — useful for lookup, useless for learning in order. Added an AI-built curriculum: ordered stages per deck and a default '순서대로' view that walks the cards from beginner to advanced, numbered.

Jun 13, 2026 · 2 min

The owner failed an interview for a specific reason: he couldn't parse fast native English in real time and the conversation broke down. The whole platform was speaking-heavy, and its listening surfaces showed the partner's line as text — so the ear never trained. Built a no-subtitles fast-listening drill that reproduces the interview condition.

Jun 13, 2026 · 1 min

On the phone, the detail-modal header rendered the title and situation text one word per line. The header was a single flex row where the action buttons ate the width and the flex-1 title block collapsed. Stacked the header on mobile and grouped the buttons into a wrapping container; fixed across phrases, concepts, ai, and checks.

Jun 13, 2026 · 1 min

Move Decks are the engineering first-principles the sparring and AI-audit graders reason from, but each move only had a seed line, a raw-English line, an explanation, and probes. Enriched all 25 via generate-then-verify: each now carries the real tools it applies to, its actual trade-offs (always shown), a concrete Offer-FSM example, and a verified code snippet.

Jun 13, 2026 · 1 min

The owner named a real fluency gap: he knows the concept but not the English term, so he asks questions clumsily. Built a reverse-glossary mode — dump a raw description and get the precise term(s), a one-line definition, the polished way a senior would ask the question, and related terms.

Jun 13, 2026 · 2 min

A cold content-quality inspection of every screen found the platform broadly interview-ready, with the real risk being self-contradicting numbers and labels — the things said out loud in the interview. Fixed nine: a costing story whose throughput and line counts disagreed with themselves, a TTS voice that was computed per accent then hardcoded to alloy, slug labels leaking on the intro screen, and a few mismatched copy and model labels.

Jun 13, 2026 · 2 min

Ran the same generate-then-adversarially-verify accuracy pass over the system-design and DB content (sdtopics.ts, lld.ts, dbperf.ts). Eight confirmed errors: a CREATE TABLE/INDEX pair that fails to run, two wrong read:write ratios spoken verbatim, a DynamoDB-tagged Postgres schema, and several cases where the prose claimed the code handled an edge it didn't.

Jun 13, 2026 · 2 min

The /sparring drill was a stateless single-turn judge, so it couldn't corner you on your own earlier answers. Gave it conversation memory, a relentless escalating prompt, teach-on-miss (explain the concept when you're lost, then re-ask), and switched the model to gpt-5.4 — which required swapping max_tokens for max_completion_tokens and dropping the custom temperature.

Jun 13, 2026 · 2 min

The app is used all day on a treadmill via iPad. A 35-screen audit found tiny tap targets, sub-14px drill content, and hover-only completion checks as the recurring killers. Fixing SiteHeader, TrackedList, and SpeakGate plus the talk screen fixed the high-severity issues across 20+ screens at once.

Jun 11, 2026 · 1 min

A deploy script used the short service name instead of the CloudFormation-generated one; update-service threw ServiceNotFoundException, no rollout happened, but the final health curl hit the old container and printed success. Verification now compares running-task image digest to the pushed ECR digest.