Solo developer builds Kotlin Multiplatform manga translator, cutting per-page cost below half a cent

·12 views

A solo developer has released Mangit, an iOS and Android app that translates manga, manhwa and comic pages by detecting speech bubbles, reading the text, translating it and re-typesetting the translation in place. The app is built with Kotlin Multiplatform and Compose Multiplatform for a shared UI and logic layer, with a Firebase backend and a self-hosted processing pipeline on Modal. The developer first used a large image model costing about $0.05 per page, then switched to smaller specialised models, bringing the cost down to roughly $0.001 to $0.004 per page. That reduction is what made a free tier viable, offering three free pages to start and three per week afterward. The developer noted that rendering non-Latin scripts such as Thai, Arabic and Hindi was among the hardest challenges, since many fonts fail to display them.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

GitHub Reports Incident Affecting Webhooks and Actions

GitHub has posted an incident notice on its status page concerning disruptions to its webhooks and Actions services. The incident was shared on Hacker News, where it drew 23 points and 14 comments from readers. The provided source material does not include details on the exact cause, duration, or scope of the disruption. Users relying on these services may wish to check GitHub's status page for the latest updates.

0 comments Read more at Hacker News

ProgrammingDEV Community ·

Cursor-based pagination for multi-tenant RAG ingestion at 10k documents

The article argues that ingestion for a multi-tenant help center should use tenant-scoped cursor pagination over a stable snapshot rather than offset pagination, which becomes a correctness and index-cost problem as content grows. The author describes ingesting documents in bounded pages ordered by update time and document ID, then chunking and upserting vectors with deterministic keys so repeated runs stay idempotent. Page size and chunk size are presented as tunable decisions to be measured against the document mix, not fixed constants. Metadata such as tenant, revision, and access controls is kept with each chunk so retrieval can enforce tenant boundaries before ranking. The piece is written from the perspective of a logistics SaaS workload with carrier rules, customs notes, and warehouse procedures.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Go Review Jobs: Handling Long Document Extraction and Timeouts Without False Completion

The article explains how to run bounded review jobs that turn long documents into JSON while keeping an explicit incomplete state after a timeout. It argues that a parseable response does not prove a review finished, so deadlines, token budgets, and evidence coverage should be tracked separately. Failures such as local deadlines, transport errors, context-budget rejections, and validation problems are recorded in distinct categories because each calls for a different fix. The author advises against blind retries, since a timed-out request may still have run remotely, and recommends deduplicating published findings by review revision and finding identity. Chunking should follow source boundaries and fit the selected provider's tokenizer limits, with file paths and line numbers kept outside the model's output.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Invisible Unicode Characters Can Quietly Break Email Templates and Filters

A scenario is described in which marketing copy pasted into an email template passed a visual check but caused a rendering problem and a missed filter match. Invisible Unicode characters such as direction controls and zero-width characters occupy positions in text without displaying anything, and they often arrive unnoticed through copy-paste from documents or web pages. These characters can reorder displayed text, as in the file-name disguise example, and can split keywords so content filters fail to match them. The article notes that a 2021 research effort, known as Trojan Source, showed similar tricks could make source code appear different to reviewers than to compilers. Developers can detect such characters with a regular expression in CI pipelines, though the article cautions that some invisible characters are legitimate in certain languages and should not be blindly removed.

0 comments Read more at DEV Community