Localized reading
मुझे increasingly लगता है कि भविष्य का सॉफ़्टवेयर control flow के कोड को «fuzzy» निर्णयों के लिए छोटे neural programs के साथ जोड़ेगा। मैं ProgramAsWeights के साथ यही खोज रहा हूँ; यह बताता है कि इन neural programs का स्रोत क्या है: वे अंग्रेज़ी विवरणों से «compile» होते हैं। उदाहरण के लिए, मैंने 30 neural programs को decision tree के साथ मिलाकर एक course वेबसाइट असिस्टेंट बनाया। यह chatbot जैसा दिखता है, लेकिन लोकली चलता है। हर छोटा प्रोग्राम «इसे किस विशेषज्ञ के पास भेजना चाहिए?» जैसे सवाल संभालता है और कोड पूरे flow को नियंत्रित करता है। इसे यहाँ आज़माया जा सकता है...
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
- 13.5 हज़ार
- 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
मूल देखें ↗स्रोत
This independent archive preserves a public post with attribution. Text, media, account details and trademarks belong to their respective owners.
