Three unit-1.1 lessons with gpt-oss-20b through LM Studio and the server —
the first real model on the reworked turn. The letter-level check went out
right, and the +25 clamp held: a reported 80 on the first answer was stored
as 25. What failed was how the model wrote its blocks, a different way each
session. All three transcripts are in test/fixtures/, verbatim, and each
failure below is a test against them.
Marks lost. The prompt asks for `여덟 | wrong | 여덜`. The first session wrote
`we | wrong | 우라 → 우리`, English prompt first; the second wrote no ::result
at all and marked only in prose, `✗ 나 | I (humble) → 저`. evidence.ts keys on
the first field of a ::result row, so nothing was ever recorded — no
evidence, no schedule, no confusions, and a 다지기 review that could never
close. The artifact would have lost them the same way. domain/marking.ts
attaches each mark to its word only where that is unambiguous: one Korean
word first, or through a prompt of the exercise he answered, read via that
exercise's ::words as the letter check reads it. With no ::result block the
✓/✗ lines are read on the same terms, so a mark can never name a word the
exercise did not ask for; a mark on a whole sentence is still dropped. What
he mistook a word for is taken from what he actually wrote whenever the mark
itself gives no other word — the third session put the right answer there.
Its third session, marked through all of this: 20 evidence rows, 20 cards.
Progress on requests. The prompt allows marks, ::confirmed and ::progress
only in reply to an answer. The model wrote ::progress on every message, and
three requests for a new exercise took the unit from 50% to 80% with nothing
answered. A reply to anything but an answer now changes none of them.
Feedback swallowed. The model closed no blocks, so lib read what followed
each one as rows: "your score is about 5%" became a result row the student
never saw, and a "---" became a recall item he was asked to write in 한글.
Another session fenced every block in ```. gloss.ts now decides every
block's extent from the raw text — at "::", the next block, a rule or fence
line, a blank line with no row after it, or for the piped blocks the first
line without a "|" — and hands lib the blocks properly closed. The gate
audit, now run through the parser the lesson uses, still flags 7 and 2.
Answers given away. Translate rows came with their meanings ("나 | I") and
recall hints were the answers ("two | 이"). A translate row keeps only its
Korean line, and a recall hint that is the expected word, or any word the
message declares, is dropped.
Also: the spelling a recall prompt expects now keeps its qualifiers. With 나
"I, me (casual)" and 저 "I, me (humble)" in one list, "I (humble)" matched
나: no letter check was sent, and the mark for 저 was filed under 나.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
38 lines
7.2 KiB
JSON
38 lines
7.2 KiB
JSON
{
|
||
"source": "gpt-oss-20b (LM Studio) through server/src/backends/openai.ts, unit 1.1, 16 Sep 2026, third session. The whole transcript, verbatim. Every block wrapped in a markdown code fence; ::result third fields hold the right answer rather than the slip; recall hints are the answers.",
|
||
"turns": [
|
||
{
|
||
"role": "user",
|
||
"body": "Let's start unit 1.1 자음과 모음 (Consonants & vowels). Give me the full introduction, then a first exercise."
|
||
},
|
||
{
|
||
"role": "assistant",
|
||
"body": "Welcome to Unit 1.1: **자음과 모음** – the consonants and vowels that make up Korean syllables. \nIn this unit you will learn the ten basic vowels, the plain consonants, and how a single consonant plus one vowel creates a block (a “syllable”). We’ll keep it simple: no final consonants, no compound vowels, no tense or aspirated consonants.\n\n**What you’re learning now**\n\n1. **Plain consonants** – ㄱ ㄴ ㄷ ㄹ ㅁ ㅂ ㅅ ㅇ ㅈ ㅎ \n These are the first letters you’ll see in any Korean word. \n2. **Ten basic vowels** – ㅏ ㅑ ㅓ ㅕ ㅗ ㅛ ㅜ ㅠ ㅡ ㅣ \n Each vowel is a block on its own or combined with a consonant to form a syllable. \n3. **Blocks (syllables)** – one initial consonant + one vowel, no final consonant. \n For example: “가” (ㄱ+ㅏ) and “나” (ㄴ+ㅏ). \n\n**Why this is important**\n\nKorean is written in blocks that are each a syllable. If you can read the shape of every block, you can read any word without having to know how it sounds. We’ll start with the simplest shapes so you don’t get lost.\n\n**Common mistakes beginners make**\n\n- Mixing up consonants that look similar: ㄱ and ㅋ, ㅂ and ㅍ, ㅅ and ㅎ. \n Remember we only use plain consonants here – no aspirated or tense versions. \n- Forgetting the vowel part of a block. \n Every block has one vowel; if you miss it, the whole syllable becomes unreadable.\n\n**Examples to keep in mind**\n\n* 가 (ㄱ+ㅏ) → “ga” \n* 나 (ㄴ+ㅏ) → “na” \n* 바 (ㅂ+ㅏ) → “ba” \n* 다 (ㄷ+ㅏ) → “da” \n\nYou’ll see many of these in the words we will practice. The new words you can start reading now are: **나**, **너**, **우리**, **이**, **그**, **저**, **여기**, **거기**, **저기**, **어디**, **누구**, **아이**, **어머니**, **아버지**, **나무**, **머리**, **소리**, **하나**, **바다**, **다리**. \nEach of these has only one consonant and one vowel, so they are perfect for this unit.\n\n---\n\n### First exercise: **Recall** (you write the Korean)\n\nYou’ll see an English word or phrase and you must type the correct Korean block(s) using the on‑screen keyboard.\n\n```\n::task recall\nI | 나\nYou (casual) | 너\nWe | 우리\nTwo (Sino) | 이\nThat (near) | 그\nThere (over there) | 저기\nWhere? | 어디\nWho? | 누구\nChild | 아이\nMother | 어머니\nFather | 아버지\nTree | 나무\nHead | 머리\nSound | 소리\nOne (Native) | 하나\nSea | 바다\nBridge | 다리\n```\n\n---\n\n**Words used in this lesson**\n\n```\n::words\n나 | I, me (casual)\n너 | you (casual)\n우리 | we, our\n이 | two (Sino)\n그 | that (near you or already mentioned)\n저기 | over there\n어디 | where?\n누구 | who?\n아이 | child\n어머니 | mother\n아버지 | father\n나무 | tree\n머리 | head\n소리 | sound\n하나 | one (Native)\n바다 | sea\n다리 | bridge\n```"
|
||
},
|
||
{
|
||
"role": "user",
|
||
"body": "My written answers:\nI → 나\nYou (casual) → 너\nWe → 우라\nTwo (Sino) → 이\nThat (near) → 그\nThere (over there) → 저기\nWhere? → 어디\nWho? → 누구\nChild → 아이\nMother → 어머니\nFather → 아버지\nTree → 나무\nHead → 머리\nSound → 소리\nOne (Native) → 하나\nSea → 바다\nBridge → 다리\n\n════ LETTER-LEVEL CHECK — computed by the app ════\nThis is the actual jamo comparison. Use it exactly. Do NOT work out for yourself which letter was wrong, and never call a letter wrong that is listed as correct.\n• We\n wanted 우리 [우=ㅇ+ㅜ · 리=ㄹ+ㅣ]\n wrote 우라 [우=ㅇ+ㅜ · 라=ㄹ+ㅏ]\n syllable 2 (라 for 리) — WRONG: vowel: wrote ㅏ, should be ㅣ — CORRECT, do not call these mistakes: first consonant ㄹ, batchim none\n\n(No lookups.)"
|
||
},
|
||
{
|
||
"role": "assistant",
|
||
"body": "Great work on the first round! \nYou almost nailed every word—just a single mistake in **We**. \n\n---\n\n### Your results\n\n```\n::result\nI | ok\nYou (casual) | ok\nWe | wrong | 우리\nTwo (Sino) | ok\nThat (near) | ok\nThere (over there) | ok\nWhere? | ok\nWho? | ok\nChild | ok\nMother | ok\nFather | ok\nTree | ok\nHead | ok\nSound | ok\nOne (Native) | ok\nSea | ok\nBridge | ok\n```\n\n### Progress\n\n```\n::progress 94 | You’re almost done with this unit—just one mistake to fix.\n```\n\n---\n\nNow let’s reinforce a few new words that we haven’t practiced yet. \n\n```\n::task recall\nI | 나\nTwo (Sino) | 이\nThat (near) | 그\nI (humble) | 저\nHere | 여기\nThere (there) | 거기\n```\n\n### Words used in this lesson\n\n```\n::words\n나 | I, me (casual)\n이 | two (Sino)\n그 | that (near you or already mentioned)\n저 | I, me (humble)\n여기 | here\n거기 | there\n```"
|
||
},
|
||
{
|
||
"role": "user",
|
||
"body": "My written answers:\nI → 나\nTwo (Sino) → 이\nThat (near) → 그\nI (humble) → 나\nHere → 여기\nThere (there) → 여기\n\n════ LETTER-LEVEL CHECK — computed by the app ════\nThis is the actual jamo comparison. Use it exactly. Do NOT work out for yourself which letter was wrong, and never call a letter wrong that is listed as correct.\n• There (there)\n wanted 거기 [거=ㄱ+ㅓ · 기=ㄱ+ㅣ]\n wrote 여기 [여=ㅇ+ㅕ · 기=ㄱ+ㅣ]\n syllable 1 (여 for 거) — WRONG: first consonant: wrote ㅇ, should be ㄱ; vowel: wrote ㅕ, should be ㅓ — CORRECT, do not call these mistakes: batchim none\n\n(No lookups.)"
|
||
},
|
||
{
|
||
"role": "assistant",
|
||
"body": "You’re getting the hang of it! \nTwo small mistakes—let’s fix them.\n\n---\n\n### Your results\n\n```\n::result\nI | ok\nTwo (Sino) | ok\nThat (near) | ok\nI (humble) | wrong | 저\nHere | ok\nThere (there) | wrong | 거기\n```\n\n### Progress\n\n```\n::progress 98 | You’re almost finished with this unit—just a couple of words to practice.\n```\n\n---\n\nNow let’s practice the two words you missed. We’ll do another recall exercise, and we’ll add one new word that hasn’t appeared yet: **너** (you, casual).\n\n```\n::task recall\nI (humble) | 저\nThere (there) | 거기\nYou (casual) | 너\n```\n\n### Words used in this lesson\n\n```\n::words\n저 | I, me (humble)\n거기 | there\n너 | you (casual)\n```"
|
||
},
|
||
{
|
||
"role": "user",
|
||
"body": "My written answers:\nI (humble) → 저\nThere (there) → 거기\nYou (casual) → 너\n\n(No lookups.)"
|
||
},
|
||
{
|
||
"role": "assistant",
|
||
"body": "Excellent! All three words were read correctly.\n\n---\n\n### Your results\n\n```\n::result\nI (humble) | ok\nThere (there) | ok\nYou (casual) | ok\n```\n\n### Progress\n\n```\n::progress 100 | You’ve mastered all the basic blocks in this unit. Ready to move on to the next one!\n```"
|
||
}
|
||
]
|
||
}
|