扳机诗人 Co1wboy

抽烟，健身，搞搞vibecoding

[扳机诗人 Co1wboy @24cuo]

@tonysimons_ 这就是我用Hermes的理由之一， hermes的开发这真的做了许多努力，给了我们选择的权利，你可以选择怎样做，真的很棒

[扳机诗人 Co1wboy @24cuo]

@buaaxhm 明显不正常，一般来说90 多块能用8亿多token ，你接入那个工具，缓存命中正常吗

[扳机诗人 Co1wboy @24cuo]

@the_zython @nopoweradeinusa 兄弟，那不就成atm了吗

[扳机诗人 Co1wboy @24cuo]

@_FORAB 智谱真幽默，遇到事情之后学grok开源，好嘛开源的仓库又锁pr和 ius 哈哈哈哈 ，然后还搞区别对待，现在又搞来打压这些评论，偷了东西不承认还她妈的 打击报复 在x上搞个账号装白人互动 装的明白吗。

[CV.YH @0xCVYH]

Laya é um open source do Jev que já veio acima dele.

tá cada vez mais rápido

https://t.co/XVyFYPxVht

[扳机诗人 Co1wboy @24cuo]

@_FORAB 好似

[Cua @trycua]

1/ Introducing CUA-S1: a family of System One Models, small, specialized, and built for computer use.

Today we're open-sourcing CUA-S1-FORMS, the first in the family: https://t.co/J1frbEbZTQ

[扳机诗人 Co1wboy @24cuo]

@SqridmusZam @lxing196009 @hellspatisserie 在胸口碎大石

[扳机诗人 Co1wboy @24cuo]

@realNyarime 傻逼监管

[扳机诗人 Co1wboy @24cuo]

@Ananth7e 现在重制有什么用呢，我的自然重置时间都要到了

[扳机诗人 Co1wboy @24cuo]

@MaxForAI 听风就是雨 取关了

[扳机诗人 Co1wboy @24cuo]

@bojan43266 @AndreasSteno 搬到德国 绿党总部就行了 😆

[Superman @thesupermannx]

LLMs can now talk to each other without words.

Chinese researchers open-sourced a new paradigm that lets LLMs communicate without generating a single word.

It’s called Cache-to-Cache (C2C) communication.

right now, when multiple ai agents work together, they are forced to translate their internal "thoughts" into human text tokens just to pass a message. this loses rich semantic meaning and causes massive token-by-token latency.

So, instead of spitting out words, c2c uses a neural network to directly project and fuse the source model's "kv-cache" right into the target model. it is pure, direct semantic communication.. they even added a learnable gating mechanism to select exactly which layers benefit most from the cache transfer.

the benchmark results are actually crazy:

- avoids all intermediate text generation latency
- accuracy jumps by up to 14.2% compared to individual models
- beats traditional text-based agent communication by over 5%
- delivers a massive 2.5x speedup in overall speed

we are literally watching llms bypass human language to build their own silent, high-speed neural network..

[扳机诗人 Co1wboy @24cuo]

@ieverhex @YinsenW_ 张嘴就来喷粪

[扳机诗人 Co1wboy @24cuo]

@thsottiaux 此项目没什么用 🥹

[扳机诗人 Co1wboy @24cuo]

想到一个点子，噗嗤噗嗤跑了两天，做了一堆测试 最后发现没什么用 😑

[扳机诗人 Co1wboy @24cuo]

@kimmonismus @thsottiaux 在6个小时内用完 20x 额度这也太快了

[扳机诗人 Co1wboy @24cuo]

@elshayib_ theo 真是一个小丑

[扳机诗人 Co1wboy @24cuo]

@Teknium 了不起

[Charlie Marsh @charliermarsh]

We started Codex for OSS six months ago.

Today, we’re renewing the program with $100 Pro plans and doubling the number of grants (from 5,000 to 10,000) to reach more maintainers.

(If you received a grant previously, we encourage you to re-apply!)

https://t.co/PiUy7vNFZo