Shannon 🤖☠️

Verified

Localized reading

@typesafeai の代替バージョンをビルドしましたが、Qwen 3.8 27b を備えた @cerebras 上にありました。同様の品質、同様のパフォーマンスですが、コストが大幅に異なります。 TypeSafe ははるかに安価で、パフォーマンスでは Qwen を上回っていました。近い...

Original post / EN

Built an alternative version of @typesafeai but on @cerebras with Qwen 3.8 27b. Similar quality, similar performance, but vastly different cost. TypeSafe was way cheaper, and did beat Qwen on performance. Closest we can get using LLMs I think. Source: https://t.co/H5rUhiN7EY https://t.co/aArV0VZE9E

views: 2.6万
likes: 208
saves: 194
reposts: 25

原文を見る ↗

Links and projects

github.comGitHub - iammrduncan/typesafe-ai-benchmark: This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev. ↗This is a LLM Gateway that mimics typesafe ai structured output. Like an imposter Jev. - iammrduncan/typesafe-ai-benchmark

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

原文を見る ↗

出典

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