API公式価格より最大 28% お得API を試す →
Hermes
← Back to case library
Jevコーディング

Yuntian Deng

@yuntiandeng

Yuntian Deng: 将来のソフトウェアは、制御フローのコードと「あいまいな」判断のための小さなニューラル プログラムを組み合わせるだろうとますます考えています。それが私が Progra

Localized reading

将来のソフトウェアは、制御フローのコードと「あいまいな」判断のための小さなニューラル プログラムを組み合わせるだろうとますます考えています。それが私が ProgramAsWeights で研究してきたことです。これは、...という質問に答えます。

Original post / EN

I increasingly think future software will combine code for control flow with small neural programs for "fuzzy" judgments. That's what I've been exploring with ProgramAsWeights, which answers the question of where those neural programs come from: they are "compiled" from English descriptions. For example, I combined 30 neural programs with a decision tree to build a course website helper that looks like a chatbot but runs locally. Each small program handles a question like "Which specialist answerer should this be routed to", and code controls the overall flow. You can try building with it here: https://t.co/Bwgcn362bc
views
1.3万
likes
171
saves
140
reposts
21

Links and projects

Quoted post

Diogo Almeida @CompleteSkeptic

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x https://t.co/JSybNG2BKJ

This independent archive preserves a public post with attribution. Text, media, account details and trademarks belong to their respective owners.