СледваСледващо ръководство
Протокол за контекст на модела
Езиков AI
Фирми РЪКОВОДСТВО
Magic AI is a startup developing long-context models for software-development tasks.
Чуйте това ръководствоAI-разказан · ~2 min
The company says LTM-2-mini supports up to 100 million tokens, which can place substantially more cross-file code and documentation in one context; capacity alone does not guarantee correct reasoning over an entire codebase.
Magic AI is a startup developing an AI software engineer rather than only autocomplete. In its August 2024 research update, the company described LTM models, including LTM-2-mini, with a context window of up to 100 million tokens; its analogy is roughly 10 million lines of code or about 750 novels. This is a model capacity claim, not evidence that the model can correctly understand every codebase or complete every project-wide task. The update also describes a Google Cloud partnership for supercomputer development and funding announced at that time. Magic introduced HashHop as a controlled evaluation using random, incompressible hash pairs and chained lookups to test retrieval at long context lengths. Results on that constructed task measure those retrieval and chaining tasks; they do not prove arbitrary code comprehension or performance on every real repository.
Providing a large repository or selected subset as context for questions about cross-file relationships, then checking the answer against source code.
Drafting a refactor that touches related files for a developer to review and test.
Supplying code, documentation, and logs together when investigating a bug whose cause may span files.
Summarizing a selected repository context as an onboarding aid, with links or references for follow-up.
Longer contexts can allow developers to supply more code, documentation, and task details together. Reliable multi-file work still depends on retrieval, reasoning accuracy, tool execution, and verification. Future systems should be evaluated on representative codebases and tasks, including whether they find relevant distant files and make changes that pass tests, rather than being judged by context size alone.
Безплатен бюлетин
Три проверени AI истории всяка делнична сутрин, написани на достъпен език. Безплатно завинаги, без реклами.
Един имейл всеки делничен ден. Отписване с едно кликване. Никога не продаваме и не споделяме вашия имейл адрес.
Тествайте себе си
Незабавна обратна връзка за всеки отговор и сертификат за споделяне с подлежащ на проверка идентификационен номер, след като преминете курс.
Подкрепете безплатното AI образование. AI Understanding е 501(c)(3) с нестопанска цел — без реклами, без платен достъп, никога. Направете дарение
Magic AI is a startup developing long-context models for software-development tasks. The company says LTM-2-mini supports up to 100 million tokens, which can place substantially more cross-file code and documentation in one context; capacity alone does not guarantee correct reasoning over an entire codebase.
Magic describes its work as developing AI for software engineering. This is a company goal; it does not guarantee that a model can correctly handle every codebase.
Magic’s August 2024 report announced a context window of up to 100 million tokens for LTM-2-mini. Context capacity is distinct from accuracy on a task.
Magic designed HashHop as a controlled random-hash retrieval and chaining benchmark. It reduces semantic cues but does not establish broad code understanding.
Цената на стандартното внимание нараства с квадрата на дължината на последователността, така че много дългите контексти са изключително скъпи без по-добри алгоритми.
Magic обяви партньорство с Google Cloud за изграждане на суперкомпютри на хардуер на Nvidia.
Продължавай да учиш
Още ръководства, избрани за тази тема
СледваСледващо ръководство
Протокол за контекст на модела
Езиков AI