Spaces:
Running
Running
Commit History
2 days ago
-
Smart Humanize: "What should come down?" - Lower the AI score / Reduce similarity / Both. Reduce similarity rewords the sentences a similarity report matched (an uploaded report is read as a similarity report), or without a report every prose sentence, each until at most 15% of its original word sequences remain (citations, numbers, terms and layout kept, meaning checked), and still takes the AI score to 0%; the result says how much original wording remains. The Turnitin "Lower it" / "Reduce it" buttons set the goal. Goal choice styled in the Manuscript-desk look; intro mentions similarity Running
unknown +1: Claude Opus 5.5Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>7bfa845
5 days ago
-
Pricing for profit on every run: price = 5 x cost after GST and fees (was 4 x), at least Rs 49 (was Rs 10); a document lowered but not to 0% pays half (was free; half is still about 2.5 x cost), one not lowered stays free; Turnitin's set price never below cost + 30%; free tier trimmed (5 pastes a day, trial document up to 1,500 words, guests 3 pastes); Pricing page states the half-price rule; Admin -> Profit tab: net profit after GST, fees, language model, reports and the always-on GPU bill, cost of free use, paid runs needed to cover the fixed bills, runs below cost, profit by tool (7 / 30 / 90 days)
unknown +1: Claude Opus 5.5Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>662c98f
15 days ago
-
Pay as you go only: prepaid wallet with PhonePe top-ups; every run reserved before it starts, capped (Groq + deadline) and charged its actual price with a 300% margin after GST and fees; admin profit report
unknown +1: Claude Opus 5.5Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>89d4f87
17 days ago
-
Paraphrasing 10x faster: learned banned words blocked with suppress_tokens
unknown +1: Claude Opus 5.5The adaptive learner's banned-word list had grown to 5,528 token sequences on the Space. Passed as bad_words_ids it is checked in Python at every generated token (with a GPU sync each time): every Parrot call took 18-28 s, even for one sentence, and it got slower as the tool learned. Single-token bans now go through suppress_tokens (one vectorised step); banned words of several tokens are still rejected afterwards by banned_in(). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>23008bb -
Faster humanizing on the GPU Space; the automatic proofread no longer undoes the humanizing
unknown +1: Claude Opus 5.5- The meaning, fluency, clarity and vocabulary checking models now run on the GPU when the Space has a dedicated one (they ran on the CPU for every version of every sentence on every pass; HELPERS_GPU=0 keeps them on CPU). - Automatic proofread after humanizing: grammar fixes and repairs that raise the AI score are undone too (a repair put back the author's flagged wording: a live run went 0% -> 100%). If the proofread still scores worse, the humanized version is delivered and the customer is told to press Final check & proofread to apply it anyway. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>4d32393
22 days ago
-
Pricing page: pay-per-use card and a monthly / yearly switch
unknown +1: Claude Opus 5.5- New "Pay per use" card (shown when PAY_PER_USE is on): no plan or credits needed, scores first, pay to download, price shown before paying, GST included; starts at PRICE_MIN_INR. - "Plan billing" radio next to Currency: Yearly redraws the Scholar and Pro cards with the yearly price, the per-month equivalent and the saving; the monthly view keeps a one-line yearly reminder. - "Rigorous proofread" now reads "Final check & proofread, done automatically" on every card. - pricing_html(currency, billing); test for both views. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>37d9ddb -
Automatic proofread, pay-per-use charges with a pay pop-up, yearly plans
unknown +1: Claude Opus 5.5Automatic proofread - Every humanized text / document (Smart Humanize, Humanizer) goes through the final check & proofread; the proofread file is delivered. AUTO_PROOFREAD=0 = only on request. - humanizer.PROOFREAD_FOLLOWS: the humanizer's own language-model polish is skipped when the proofread follows (one final check, not two). - A failed proofread still delivers the humanized result and says so. Pay per use (plans.py, app.py) - check_doc returns "payg" for a signed-in customer without credits instead of blocking (PAY_PER_USE=0 restores the block). - usage_price(): GPU seconds x COST_GPU_HOUR_USD, idle share of the Space (COST_IDLE_FACTOR), the job's language-model cost, then PRICE_MARGIN (200%), PRICE_GST (18%), PRICE_USD_INR, PRICE_MIN_INR. - charges table; the result is locked (no file, no preview, no email, not in the run history) until settle_charge(ref). Pop-up with the price; Pay opens PAY_URL or the WhatsApp contact; "I have paid" unlocks. - Admin: pay-per-us…ca97939