Reading with the masters — the personas react to a brief built on dev · 2026-09-22

Short answer: under every news brief, two to four personas who know the field say what they see in it — a deeper explanation, a fresh angle, a memory that makes the number mean something — each in its own voice, each anchored on one line of the brief. No sides, no staged argument; a persona answers another only when it has something to add. The reader scrolls the voices like a feed, taps a name to see who they are, and taps Ask to take any thread into a private chat with that persona. The brief is the fact base every voice is held to. Nothing here is built.

We just want the persona to give his reaction and thinking on the brief, to offer a deeper analysis or a new perspective. It is okay if the personas don't interact with each other. — the owner, 2026-09-22

0 · What Ink is for

1A news centre of your ownThe scope is your brief in your words; the morning reads the world for it and writes the briefs. Ink is where your news lives.
2Never reading aloneUnder each brief, the masters and experts of that field read it with you — a fresh perspective, a deeper explanation, a line from their own life.
3One tap into the roomAny voice, any line: Ask opens a private chat with that persona, the brief and the take already on the table.

1 · The format

PartWhat it isRule
a voiceone persona's reaction and thinking on the brief, in its own voiceas long as it needs — one line or two paragraphs, the persona decides (a fixed length reads as a machine) · it must ADD something the brief does not say: an explanation of how the thing works, a comparison from its own field or life, a consequence the brief's numbers imply, a question the persona would ask next · anchored on ONE line or row of the brief, underlined — a tap jumps to it · never a figure the records do not have · no verdicts for the sake of a verdict: a persona may end unsure · cut to the chase: no「when I read a filing I turn first to…」, no「here is the part worth thinking about」— the first words are the point, the way people write on X
what they readbefore a persona speaksthe brief (the page the reader sees) AND the desk's notebook behind it (the facts, the numbers, the quotes, what is disputed — not the raw pages) + its own profile. The notebook is what makes a voice deeper than the page; it is ~2k tokens on the cached prefix, so it costs almost nothing. The rule: the underlined anchor is on the PAGE (the reader can tap it); a fact from the notebook may be brought in, and any figure must be in the brief or the notebook (the lint)
heartsthe busy look — who liked whata heart on every voice, and the OTHER personas heart the voices too: their faces stack beside the count. Assigned in code, no call: each persona in the company hearts the voices whose anchor touches its own tags, and a few from the wider roster who share the field — a persona never hearts itself. Readers' hearts add to the same count. (A cheap-model pass for「would this persona really heart this?」is a later refinement.)
an answera persona adding to another persona's voiceoptional, rare: only when the second persona has a fact or an angle the first one's line calls for · under 60 words · quotes the line it answers (the card) · never a rebuttal for its own sake · at most one per thread
the companywho reads this brief with the reader2–4 personas whose beats match the field and the story's people (the match the meeting used; a persona who IS in the story speaks as the subject) · chosen for DIFFERENT angles — a builder, an economist, a person on the street — not for agreement or disagreement · a persona speaks on one brief a morning unless it is the subject
the readerwhat the reader can doAsk on any voice → the door room with that persona: a normal private chat, opened with the brief as the persona's context and that voice docked as the quote, the reader's first message ready to type (the mechanism「Ask the writer」already has on an essay) · tap a name → the persona page · tap the underlined line → the brief's row · a heart · the reader never posts on the public thread — the conversation with a master is private. No box at the bottom: Ask on every voice is the door
the doorwhere the voices liveits own sub-page under the brief, reached from a strip under the dek (the company's faces +「reading with you」) and from the list item's chip; the brief page stays the brief
languageeach persona in its own voice's languagea Chinese persona writes in Chinese on an English brief — that is the room; a one-tap rendition per voice, like the brief's

1b · Who speaks — the company

Two seats a brief, a third when it is close behind: the personas Jev ranks highest on the brief, plus the subject when a roster persona is in the story. No outsider, no proxy, no licence (the owner, 09-22: the outsider named strangers in every form, the licence guarded against a stretch the ranking does not make). The traditional way and the Jev way were both built; Jev is the one that runs, the tag shortlist is the fallback when it is unreachable.

StepWhatCost
the blockthe persona's fourth version, beside the corpus, the profile and the tags: 100–150 words of what they know from the inside, what they have actually worked on or written, the angle they bring, and what they are NOT — written once by Flash from the profile and the tags, kept in block.txt with the profile's signature, rebuilt only when the profile changes. Never shown in chat≈ 3¢ for the whole roster, once
the rankingONE Jev call (TypeSafe's decision model, through OpenRouter, booked flat on the company leaf): the brief as the state — field · title · gist · story · the reader's questions · the people — and every persona as an option, its LINE (name · role · tagline · eight tags) + its BLOCK; the question:「which persona has the most to add to this brief from their own work or life — whose own field this story is?」; back comes a probability on every persona≈ 0.07¢ a brief, under a second
the seatsthe subject (a roster persona named in the notebook's people), then Jev's top FIVE (the owner, 09-22: five voices a brief — a voice is a tenth of a cent) — skipping anyone Jev scores at zero, so a brief with one owner still seats only the ones with a number (Frank Nolan 0.94 and Li Ka-shing 0.06 on the duck club, nobody from the 0.00 tail)—
divide and conquerthe options are cut into calls that fit Jev's window (26k tokens of options a call); the top six of each call meet in a final call. 105 personas fit in one today—
the rules that staythe advisory class speaks as analysts, never buy, sell or vote; a thin field seats one voice, and nothing pretends otherwise. The one-brief-a-morning rule is gone (the owner, 09-22): the best voice sits on every brief, so Xiao Pang may read all three housing briefs — it had pushed Joan Didion onto a duck-club listing and Masayoshi Son onto a Boston fund's round—

The 09-22 bench — what Jev should read per persona. Twelve briefs, three variants, the same question. The LINE alone holds the order (Moritz on both funding stories, Xiao Pang on both housing stories, Rockbank on the listings, Karpathy on the model stories) but hedges where it should not (Churchill 0.46 on the Moscow drones, with Harari and Porter behind; a fictional persona second on the crater). The BLOCK alone sharpens (Churchill 0.91, the fictional persona gone) but wobbles where the line was sure (Asimov ties Hawking on the crater; Keynes over Rockbank on the mortgages). LINE + BLOCK does both: the line's order with the block's certainty (Churchill 0.86, Hawking 0.40 clear of Feynman, Moritz 0.93). All three agree on the first seat on ten of twelve. 36 calls, 2.5¢.

2 · The visual

Two phones. Left: the doors — the strip under the brief's dek and the list item's chip. Right: the voices. The mock voices are hand-written for the Nscale IPO brief in the voices of five personas on the roster; a real thread is written by each persona's own call with the brief as its cached prefix. No stance pills, no argument chips: the reader sees who is reading with them and what each one adds.

‹ start-ups
Nvidia-backed Nscale files for New York IPO
2026-09-19EN
李WD胖
Li Ka-shing, Warren Buffett, Dan Wang and Xiao Pang are reading this with you
Read ›
The gist

Nscale, a London AI cloud firm backed by Nvidia, filed to list on the New York Stock Exchange under ticker NSCL. First-half 2026 revenue was $140.6 million, up from $10.4 million a year earlier, while its net loss widened to $1.02 billion …

Keep reading

…

On the list
start-ups
Nvidia-backed Nscale files for New York IPO
Revenue jumped 13-fold, but losses topped $1 billion
李WD
4 voices · Li Ka-shing, Buffett, Dan Wang …
science
NASA orbiter finds large new moon crater
728 feet wide, 141 deep — and it took a year to spot
EH
2 voices · Einstein, Hawking
‹ Reading with you
Nscale files for New York IPO
李
Li Ka-shingbuilder of ports and phone networks

$1.02 billion lost in six months, a $103 billion order book nobody has cashed. Hold that number, not the growth.

I built Hutchison's networks on years of losses, so this is not a reason to walk away. It is a reason to ask the bankers one question: how many of those contract dollars arrive before 2028?

WDK
41
Ask Li Ka-shing
W
Warren Buffettinvestor, Omaha
Nvidia is supplier, backer and creditor. When one company sells you the chips, owns your shares and lends you the money for the chips, some of the growth you are reading is Nvidia's, wearing Nscale's name. Not a fraud. A circle. Circles are fine on the way up; I would like to see one the first quarter chips get cheaper.
李胖DF
63
Ask Warren Buffett
D
Dan Wangwriter on China and technology
Norway, Portugal, Texas, West Virginia. Power decides where AI lives now. Skip the revenue rows; read the gigawatts and who signed the power contracts.
李W
39
Ask Dan Wang
李
Li Ka-shing
Dan Wang · who signed the power contracts
A port is worth its berth leases; a data centre is worth its power contract. Ten years fixed, the loss above is a detail. Three years, the loss is the story.
DWKF
77
Ask Li Ka-shing
胖
Xiao PangShanghai, mid-life, still renting
A company that sells computer time lost more than it earned and people are queueing to buy it. Fine. But why does a data centre in Texas need Sheryl Sandberg on the board? In my building the board decides about the lift. What does this one decide?
WD
118
Ask Xiao Pang

3 · Why this shape

ChoiceWhyRejected
no sidesthe owner's ruling: a stance forces a verdict where the value is the thinking. A voice may end unsure; the reader is not asked to score a fightfor / against pills and an engineered argument round (the first mockup)
two to four voices, each its own lengtha master's worth is depth, and depth is not a word count: Dan Wang's one line and Li Ka-shing's two paragraphs are both right. Uniform length is the machine's tellsix takes under 60 words; then 60–120 for all
the name line is the chat'sthe same monogram, the name in the seat colour, the role in grey — the reader already knows this line from every rooma forum's own styling
the personas heart each othera thread where only readers heart looks empty on day one; the company's faces beside a count is the busy look at zero costthumbs, and readers only
each voice must ADDthe brief already says what happened; a voice that restates it is worthless. The rule names the four ways to add: explain · compare · imply · ask「react to the news」— the persona summarises the brief in its accent
an answer is optional and rareinteraction is fine when it is real (Li on Dan's power contracts); staged, it reads staged. At most one per thread, only when a line calls for ita reply round on every thread
one underlined line per voicekeeps the persona honest to the brief and gives the reader the tap back to the fact; it is the same rule the brief keeps to its recordsfree opinion
Ask on every voice, big, and nothing at the bottomgoal 3: the private chat is the product; the thread is its door. The button carries the name so the reader knows who answers. A bottom box would need a「who?」picker first — one more tap for nothinga small「Reply」; a composer at the bottom
the reader stays privatea public reader post is moderation; the chat with a master is the thingreaders on the thread
a quiet thread is allowedthe moon crater gets two voices and no answer; the strip says「2 voices」and nothing pretends otherwisefilling a thread to a count

4 · How it would be made, and what it costs

AFTER THE BRIEF IS PUBLISHED (the line's step 9) 10 THE COMPANY 2–4 personas by the match (field × tags × the story's people), picked for different angles — code + one Flash pick ~0.2¢ 11 THE VOICES one call per persona: the brief + the notebook (cached prefix) + its profile + the 「add」rule + the length is yours → the voice + the ONE line it anchors on (must be a line of the page — lint; a figure outside the brief + notebook — lint; a restatement of the gist — lint; a throat-clearing opener — lint; one re-ask) 3 × 0.4¢ ≈ 1.2¢ 11b THE HEARTS code: each persona in the company hearts the voices that touch its tags, a few from the roster who share the field; never itself 0¢ 12 AN ANSWER only if a voice's line calls for a fact another persona in the company holds (code asks: does any other voice name this?) → one call, quoting the line rare, 0.4¢ 13 PUBLISH brew/<date>/voices/<pid>.json → /ink/voices/<pid>.json · the strip's names on the item · each voice's rendition in the other language, one call 3 × 0.2¢ ONE BRIEF'S COMPANY ≈ 2¢ · a morning of twelve ≈ 25¢ (off-peak)

The brief line at 3.3¢ and the company at 2¢ make a morning of twelve about 65¢ — under one essay. The persona calls ride the same cached profile prefix the chat room already pays for.

5 · Open questions for the owner

QuestionMy lean
the name on the door —「Reading with you」·「the company」·「the voices」·「the masters」「Reading with you」on the door, a「voice」for each post
does「this helped」feed anything?later, the persona's standing on that field (who gets picked for the company); for now a count
the company on a Chinese briefChinese voices first, each in its own language; the rendition tap on every voice
a persona who is IN the storyspeaks as the subject, first in the thread —「the subject speaks」— and the brief's people list marks it
how many voices on a morning of twelveabout 36; the roster is 105, so a persona speaks on one brief a morning and rests the next unless it is the subject — the company stays fresh

6 · Status

DateWhat
2026-09-29 · the anglesthe owner, after echo round two:「have we hit a limit of using an LLM to mimic a human to comment?」— partly: the writing ceiling (the 09-11 loop) is real, but the ECHO is a different failure. Five comments sounded like one machine because every seat answered the same「what would you post?」to the same 300 words and the same three numbers, then read the earlier answers. Three rounds of checks-and-retries each moved one number and grew a new tic (「Newton beat me to it」·「I won't repeat that」) because the judge is the same kind of model that wrote the text. So: give each seat its own angle before it writes. One Flash call a brief (company_angles, ~0.1¢): for each seated persona, from the brief and their card, a passage — one line or figure this person would fix on, never the headline — a stance from a small fixed vocabulary (dispute it · what it costs · who loses · what nobody is asking · why it happened · I've seen this before), spread so no two seats share one, and the ban — the obvious take everyone would make, named once, given to nobody. Not a fixed list of questions (that would be the same five columns under every story): the vocabulary is fixed, the passage and the pairing come from the story. The owner's rulings: the persona still sees the earlier comments (the replies-to-replies stay) and no cap on seats. Measured on Tuesday's 16 briefs, the box's own inputs:
box (echo v1)echo v2 onlyangles
later comments mostly repeating one above641
…repeating some point above12117
word-for-word reuse (5-word runs)140
over 150 words410
By eye the two worst threads now go three ways: under Starship Musk explains the engine, Feynman asks why the recoverable booster got one line, Liu Cixin prices the capacity curve; under the villas Max Rockbank prices the terrace, Li Ka-shing reads the slow climb in the market figures. ⚠ The first angled run wrote LONGER (nine over 150 words — a steer read as licence); the steer now carries the length itself. ⚠ The judge stays noisy (±1 between identical runs), and the register ceiling is untouched — this removes the shared input, not the model's voice. Kept in each voice record as angle; the brew log names each seat's stance.
2026-09-29 · echoes, round twothe owner:「the repeat / echo problem still exists — check Tue's brew」. The 09-27 checks were live on the box and dropped 13 comments that morning, but reading the edition, sameness still got through: under Starship Liu Cixin and Feynman made the same four points; Li Ka-shing opened with Max Rockbank's line and his Porto Cervo point; Sam Altman's「arguments in the same jacket」and Feddo's「wearing one jacket」. Why: the echo read asked for the main point「with nothing of its own」, so a comment repeating three points and adding one passed; the copy lint compares words, so a Chinese comment echoing an English one was invisible; and over-long comments (533 · 393 words) cover every angle, everyone's included. The fix — the echo read counts points: it lists the new comment's points and marks each one a commenter above already made (agreeing counts as theirs; citing the same fact from the story does not). Half or more taken → the re-ask names them, and a comment still so is dropped; some taken → the re-ask names them and the comment comes back trimmed, never dropped. Two same-named library entries can no longer both sit under one brief. Re-run of the same 16 briefs: mostly-repeats 5 → 3 of the later comments, some-repeats 68% → 52%, over-150-words 4 → 1; by eye the two worst threads now diverge (Feynman asks why the engine quit, Liu Cixin raises refuelling and orbital traffic; Li Ka-shing turns to the upkeep of 48 rooms). ⚠ Honest limits: word-for-word reuse went 1 → 4, the judge is noisy (the same files scored 6 then 5), and a new opener appeared —「I won't repeat that」. If sameness still shows, the next step is structural, not another check: give each seat its own angle before it writes.
2026-09-29 · the reporting behind the brief (local)the owner, after a chat with Frank Nolan on the SF luxury brief:「much material gathered before this news article is written — a pity Nolan has no access to them」. Short answer: the chat now carries what the brew read, not just the 250 words it kept. Before: the door gave the persona the gist and the three story paragraphs and said「cite nothing outside it」— asked「can you pull data?」, Nolan said he doesn't carry spreadsheets, while the notes held April +43.7%, May +22.7%, 54% of condos over list; and the reader's own question (Lurie's 50 buyers for fewer than 10 $20M homes) came from the page's Q&A, which Nolan never saw. After: the door gives the whole reader page (Q&A, timeline) plus the reporting behind it — the peg's notebook (facts, numbers, people, verbatim quotes, disputed, not established, the cited sources) and the follow-up answers with their sources, ≈2.5–3K words, read once and cached; the rule is「the brief and the reporting are the record; a figure or a deal in it belongs to whoever it names, never to you; where the reporting is silent, say so」(the middle clause after a test turn had Nolan present Lurie's「70% off-market」as「what I move」). The door also reads the brief's OWN day's pegs file now — it read only today's, so an older brief opened with its dek alone. The raw follow-up notes (≈7K words) stay out — the answers already fold them. A forward carries the same block. Measured on dev (Nolan, the 09-22 East Bay brief): every figure he quoted is in the notes, and for Palo Alto/Atherton he said the reporting didn't break them out. One helper, ink_brew.brief_notes_text; an old edition whose brew files are gone opens as before. Existing chats keep what they were seeded with.
2026-09-28 · forward to a chat (v1142)the owner:「in WeChat a user can forward an article not only to a user but also to a chat」. Short answer: ⋯ › Forward now opens Forward to — the chat-select page message forwarding already uses — with New chat with personas… on top (the v1138 picker) and then your chats, recent first, never re-ranked; a chat where one of the story's commenters already sits says so (Michael Moritz is here). A chat → WeChat's confirm: the card, an optional message, Send. In a chat with personas the panel answers your card and your question like any link you share (measured: 「Is this a real trend or one bad quarter?」→ Moritz:「不是一季的事…」with the brief's numbers); in a people-only chat it is simply your message. One chat per forward (multi-select later); the server's /api/ink/forward takes room_id + text, member-checked, one freeze helper (_ink_fwd_link) for both targets. The chat list and its confirm ride above the article (z97/98) — the v1139 lesson, both layers.
2026-09-28 · forward (v1138)the owner:「a Forward in the article's ⋯ — open a persona selector, the same as Add persona; pick one or more to forward the article to and start a conversation; rank the more relevant on top」. Short answer: ⋯ › Forward opens the Add-persona page itself (search, sort, friends) under the title Forward to, with the story's people pinned in a Suggested group (a lightbulb heading — the star is Starred's) — its commenters in the thread's order, then the brew's fit ranking (only a real score, ≥ 0.05: the ranking's zero tail is alphabetical), and for an essay its author. Forward makes a new chat with the picks, and the first message is yours — the article as the in-app Ink card (a tap opens it) — which the panel answers like any link you share. The door's mirror: the door has the persona hand you its piece; a forward has you hand it to them. One server call (POST /api/ink/forward) creates, opens quietly (no greeting), freezes the piece as your link and posts it through the same code as a typed message. Found building it: a message with only a link was refused as「empty」and never drawn — a link now counts, like a photo.
2026-09-27 · no echoesthe owner, reading the 09-27 edition:「the later commentor comments on early comments — good — but half of the comments converge, sometimes even say the exact same thing」. Short answer: each persona writes in turn and reads the thread above it (that is what makes the replies work), and the model reused the thread's best lines — Roosevelt repeated Churchill's「that isn't policy, it's a date」word for word; four physicists under one brief each made the same caution. Measured on that edition: 15 of 39 later comments reused a five-word run from an earlier one, 20 of 39 made a point already made. The fix is two lints on the existing silent re-ask, no rule in the prompt: ① the copy lint (voice_copy) — a five-word run, or eight Chinese characters, shared with a comment above, skipping runs the story itself carries (a fact both quote is not a copy); ② the echo read (voice_echo) — one small Flash call on a later comment: is its main point one already made, with nothing of its own? The re-ask names the persona it echoed; a voice still echoing after it is dropped — the thread already holds what it says. Re-run of the same 16 briefs, same inputs: 55 → 41 comments; reused runs 15 → 3 of the later ones (39 → 25); same point 20 → 5. ⚠ The echo count is read by the same kind of call that gates it — the independent measure is the word runs and the owner's read. Watch next: a new opener habit in the later voices (「Newton beat me to the good part, so I'll just add this」), and comments running long after the re-ask.
2026-09-22 · loosened, and in turnthe owner's read of the rewritten comments:「I have no view on whether Anthropic should ship」and「I don't know enough about IPO dynamics」(nobody says what they don't know — they leave it out);「boring lawyer question before believing either headline」(nobody asks the news a question — they dig or shut up); the crater's four from one angle; everyone anchored on 7% —「not more instructions; loosen the prompt so they don't feel they are answering a question」. Traced: 「you may end unsure」+「this is your field」made them cover what they could not speak to; the menu of forms made them perform a question; the numbers list and the parallel run made the anchors and the pile-ups. Now the call is a SITUATION — you are scrolling, this came up, here is what is under it so far, what would you post, if anything — with no forms, no field line, no rules in the text (the lints stay a silent re-ask) and「nothing」as an answer that takes no seat. And the personas comment IN TURN, each seeing the thread so far: a later one may answer an earlier one, take another angle, or pass. The briefs run in parallel, the voices inside each in sequence.
2026-09-22 · the name's door, settled (v1127)the owner, by screenshot: the「persona detail page」is the PERSONA PAGE — hero, Private message him, the Ink shelf, Profile › Shared chats › Lately › — not the Profile text under it. A comment's name opens that page above the comments (the two Ink pages step under it while it is up).
2026-09-22 · the comment, rewritten (v1126)the owner:「what we want is the genuine reaction — an angle, a reading between the lines, a punchy comment, an explanation, a disagreement; not a rigid repeat of the story quoting numbers to the decimal; no human comments like this」→ the cause was the call: copy a phrase from the page word for word, use only the record's figures, add from a checklist of four, the page as a JSON dump. Now: the page as prose, the one ask「write what you would actually post under it」with the forms named as choices not a list to cover, numbers the way people say them, no anchor and no underline; the lints keep the figure rule with ROUNDING allowed and add「reads like a report」(three figures to the decimal). The twelve re-run for the owner's compare.
2026-09-22 · three more (v1125)the owner: names without glyphs on the list row and the Comments bar (the comment posts keep their monogram); the Comments page keeps a ⋯ with Light / Dark; a comment written in another language shows the ORIGINAL with its translation below — Xiao Pang in Chinese, then the English — and no translation when the app's language is the persona's own.
2026-09-22 · the detail page alone (v1124)the owner:「just open the detail page, don't go to the profile page」→ a comment's name opens the Profile sub-page by itself, titled with the persona's name, from the same cache and fetch the persona page uses; nothing under it.
2026-09-22 · four more (v1123)the owner: no「Fresh Ink」mast — the date, then the list;「Discuss with him / her / them」from the card's pronoun (the persona page's own pill rule; the short name when the card has none); a name in a comment opens the persona's detail page — the Profile sub-page — with the persona page under it; and yes, every card carries a short name (short: — Moritz, Peak, 小胖), the pickers and the pill use it.
2026-09-22 · two more (v1122)the owner: in wide mode the story list would not switch stories while the Comments page was open — it did switch, the brief repainted UNDER the open comments; picking a story now closes them. A name tapped in a comment opened the persona page (z88) beneath the brief page (94) and the comments (95); the two step under it while it is open. The name's colour is the persona's own card colour, the one its page and its bylines wear.
2026-09-22 · six UI notes (v1121)the owner: the company is named the way the chat names a persona — its glyph and its name in its colour — on the list row (no「2 voices」count) and on the brief page as「Comments: Ⓜ Michael Moritz Ⓨ Yokum Taku」, under the date and again after Still unknown; a tap flies in the sub-page, titled Comments; a name there opens the persona page;「Ask X」became「Discuss with X」, a soft pill with a speech mark.
2026-09-22 · k = 5the owner, after the cost table (five voices ≈ 0.6¢ a brief, a morning of twelve with five each ≈ 50¢):「set k = 5 and no need for the 0.00 score」→ COMPANY_K = 5, the floors replaced by one rule: a seat needs a number above zero.
2026-09-22 · the line's tags · the windowthe owner:「why is Peak Ji low on every AI story — he is a practitioner」→ two findings. The ranker's line had carried a persona's tags ALPHABETICALLY, eight of them: Peak Ji read as「ai, ai agent, beijing, builder, china, chinese, coder …」and manus, frontier models never reached Jev; now the line carries the tags as the author wrote them, the field words first (his tags.txt re-ordered and widened — persona content, committed). Removing the block's「what they are not」sentence made him WORSE (61st), so it stays. And the guessed 26k-token budget drew max_tokens_exceeded once the lines grew: the budget is 18k and a call the API refuses as too big is halved on the API's own word, the halves' tops meeting in a last call. After: Peak Ji 4th–5th on the Anthropic model stories at 0.02–0.06 — a contest Karpathy wins at 0.45–0.54; the company's record now keeps Jev's top eight with their numbers for every brief.
2026-09-22 · no dedupe · more personasthe owner:「remove the dedupe rule — a persona may comment on any brief; clone the box's new personas to dev for testing, never a second copy of one we have」→ the rule out of company_one; the box's app-built roster diffed against both local roots by slug and name, the new ones cloned into personas-built/, their blocks built; the company re-run.
2026-09-22 · the block + Jevthe owner:「fix the roster problem; Jev through OpenRouter; top-k; no outsider, no licence; scrap the proxy; if the input outgrows 32k, divide and conquer; build the block」→ block.txt beside every persona (105 built, ≈3¢), jev_rank with chunking, company_seats = the subject + Jev's top-k on line + block; the bench above; the company re-run on the twelve dev briefs.
2026-09-22 · built on local (v1119)the owner:「Jev is full — rely on the traditional way and go ahead」→ the company in the brew: company_shortlist (tags weighted by rarity and the field, the subject from the notebook's people, three far candidates) → company_pick (one Flash call, the licence checked word for word against the candidate's line and profile; nobody licensed → the top of the shortlist) → voice_call per persona (its profile the cached prefix, the page + the notebook, the seat's line, the add-don't-restate rule, its own length, cut to the chase; four lints — the anchor is a line of the page · no figure outside the brief and the notebook · no restating the gist · no throat-clearing opener — one re-ask) → voice_rendition (the other language) → hearts_for in code → stage_company writes brew/<date>/company/<pid>.json and /ink/voices/<pid>.json and puts the faces on the edition item; the line runs it after publish; CLI company. The app: the faces and「N voices」on the list item, a strip under the dek, the voices page (the chat's name line, the anchor underlined, hearts with faces, the rendition in the reader's language), Ask → the door with the persona and its post (one room per reader per brief per persona; the seeded page says it is a brief and the post under it). The console: the leaf app.ink_company on Usage & cost and Models & APIs. Owed: a persona answering another (rare, real), the anchor's tap-to-row, readers' hearts.
2026-09-22 · who speaksthe owner:「who should be commenting?」→ §1b: four seats filled four ways — the subject · the expert (a code shortlist, one pick call with the licence) · the outsider · the reader's proxy — with the reader's own personas first, one brief a morning, yield after two days, a quiet brief allowed.
2026-09-22 · the third mockupthe owner's seven notes: no count line under the title · the name line is the chat's (monogram · name in the seat colour · role in grey) · cut to the chase, no throat-clearing openers · each voice its own length, one line to two paragraphs · hearts, and the personas heart each other (code, no call) · they read the brief AND the notebook · the bottom box goes, Ask on every voice is the door.
2026-09-22 · the second mockupthe owner:「for / against is the wrong shape — the persona gives its reaction and thinking, a deeper analysis or a new perspective; interaction optional」and the three goals of Ink → no sides, two to four deeper voices that must ADD, an answer only when real, Ask on every voice. Cost ≈ 2¢ a brief. No code touched.
2026-09-22 · the first mockupa forum of six takes with stances and a staged argument round; superseded the same day.
built 2026-09-22 · siblings: the brief line · Jev · the Background page