Interesting Engineering on MSN
OpenAI models make huge gains in modernizing decades-old software with 97.9% accuracy
OpenAI has significantly improved its models’ ability to write software in older programming languages ...
On October 19, 2026, OpenAI's official website announced an initiative to improve coding capabilities in "programming ...
OpenAI has released results for MultiLangBench, which asks models to build a SQLite-compatible engine in 20 languages, and ...
On October 19, 2026, an announcement posted by OpenAI on X caught my eye. It stated that the latest AI models are now capable ...
Track upcoming Nintendo Switch 2 games in 2026 with a scraper-and-alert bot. 12 steps, code included, from scraping to ...
OpenAI verilerine göre GPT-6 Luna, MultiLangBench testinde yüzde 40,3 başarı sağlarken GPT-5.6 Sol modeline kıyasla yüzde 78 ...
OpenAI a déclaré que ses modèles les plus récents se sont nettement améliorés dans l'écriture et la migration de code ...
【画像・ベンチマーク図表を全て見る】 OpenAIは米国時間10月19日、COBOLやFortran、Visual Basicなどレガシーなプログラミング言語について、自社モデルGPT-6シリーズのコード生成・移植能力が劇的に向上したと発表しました。
米OpenAIは10月19日、COBOLやFortran、 Visual Basic など学習データの少ない言語でのコーディング性能向上を発表した。新ベンチマーク「MultiLangBench」で GPT-6 Astra のCOBOL合格率は10.9 ...
Нейросети для кода, Study24, GPT, Claude, DeepSeek, Gemini, агенты для программирования, быстрые решения, работа с проектами, доступные в России ...
IT时代网10月20日消息，OpenAI 近日发布文章，介绍其在低资源编程语言编码能力上的进展，并开源了名为 MultiLangBench 的多语言编程评测框架。所谓低资源语言，是指可用代码与文档远少于 Python、JavaScript 的编程语言 ...
OpenAI zveřejnila nové testy pro COBOL, Fortran a další méně používané jazyky. GPT-6 Astra v nich dosáhl 87,4 procenta, ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results