Mi retweetledi
Mi
652 posts

Mi
@zarah2736
https://t.co/w0BoZ7PoyC Researcher
Tennessee, USA Katılım Nisan 2024
240 Takip Edilen8 Takipçiler
Mi retweetledi
Mi retweetledi
Mi retweetledi
Mi retweetledi
Mi retweetledi
Mi retweetledi
Mi retweetledi
Mi retweetledi

Ini berarti Wakil Presiden Republik Indonesia NYUAP? Bukannya SUAP ini termasuk KORUPSI ya? 🤓
BERARTI WAKIL PRESIDEN KITA TERLIBAT KORUPSI DONG YH? WADDUUUHH... 🤓🫵🫵
SEKALI LAGI, BERARTI KALO BENER NYUAP, WAPRES KITA KORUPSI DONG??? 🤓☝️
🥀@boxxtoc
Kalian udah tahu ini? BEM UBK mengaku salah karena telah menerima suap waktu ketemu Gibran, sekarang lagi LIVE sama pihak kampus & mahasiswa UBK
Indonesia
Mi retweetledi
Mi retweetledi

pantes belain salma segitunya, ternyata staffnya sendiri wkwk 😂😂

bubblebubbles@nihaobiatch
tandain nih ZAHRA BINTA GHANIA SAPUTRI jurusan BAHASA ASING TERAPAN D4 UNDIP angkatan 2024, perempuan yang juga merupakan seorang RAPIST ENABLER. biarkan twitt ini menjadi jejak digitalmu, may u rot in hell
Indonesia
Mi retweetledi

MANTAN TKW INI NEKAT KURAS SEMUA GAJI HASIL KERINGAT DI HONG KONG DEMI BANGUN SEKOLAH GRATIS BUAT RIBUAN ANAK PETANI MISKIN!
Lahir dari keluarga petani miskin di Bogor, Heni Sri Sundani terpaksa mengubur mimpi kuliahnya. Dia memilih berangkat jadi Tenaga Kerja Wanita ke Hong Kong. Kerja berat mengurus rumah tangga, tapi di malam hari dia tetap belajar sendiri sampai akhirnya lulus kuliah dengan predikat terbaik.
Tahun 2011, Heni pulang ke Indonesia. Hatinyanya hancur lihat banyak anak petani di kampungnya putus sekolah karena kemiskinan. Tanpa pikir panjang, dia dan suaminya menguras habis seluruh tabungan hasil kerja bertahun-tahun di luar negeri untuk mendirikan Gerakan Anak Petani Cerdas.
Lewat yayasan itu, Heni memberikan sekolah gratis, ribuan buku, dan program pemberdayaan ekonomi buat masyarakat desa. Semua dilakukan dengan tulus tanpa pamrih.
Dedikasinya luar biasa sampai namanya masuk daftar Forbes 30 Under 30 Asia tahun 2016 sebagai tokoh muda berpengaruh.
Satu wanita biasa yang memilih jadi lentera buat ribuan anak lain. Keterbatasan masa lalu justru jadi kekuatan untuk ubah masa depan generasi bangsa.
Keren banget kan?
Lo pernah dengar cerita TKW atau pekerja migran lain yang bikin prestasi luar biasa seperti ini? Atau ada sosok inspiratif di sekitar lo yang mirip Heni?


Indonesia

Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API.
Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls.
Try it: sakana.ai/fugu 🐡
GIF
English
Mi retweetledi
Mi retweetledi

to be clear, this is a closed source orchestrator on top of closed source models. if before you didn't control the models, now you don't even control which ones are used or how much. this is not "AI sovereignty"
i've also read the tech report to get an opinion on the technical stuff:
fugu (not the ultra version) is basically a classifier that selects which model at each turn is most likely to answer correctly (in other words a router). this leads to -10 points on SWE Bench pro compared to opus, gets some gains on other benchmarks but very slight. argument could be that it reduces cost, but no information about this so it's likely the opposite. they also have an autoresearch benchmark where they compare to frontier models "Model A, B and C" which is really crazy to not be transparent about what models you compare against. let's also say that this probably doesn't support adding new llm out of the box since you need to retrain the classifier
about fugu ultra, this is basically and advanced plan mode and orchestrator, this is a model that for a query outputs a plan with multiple "workflows". my understanding of workflows is that they say: "spawn model A subagents to achieve this, then use model B to judge it, then summarize this with model C" which is just a test time scaling compute strategy. i think this is an okish way to do it, but it's limited by the fact that they need to predict everything before the agents start working, which is why they limit this to 5 steps. imo you need to predict what to spawn at t+1 with the information you get at t, not with the info you get at t=0. there are also other issues such as fable 5 score on terminal bench being wrong and them being super vague and unclear about which model is in the LLM pool (they only mention closed source api one)
the biggest and most obvious issue is that they are introducing a "test time scaling" method with "best of N" over models, and they literally NEVER REPORT the number of output tokens or cost to achieve a benchmark/task
the good comparison here is not with opus, but it's opus with ultracode/workflows enable, not with kimi, but with kimi swarm ect.. very very confusing release
Sakana AI@SakanaAILabs
Introducing Sakana Fugu: A full multi-agent orchestration system accessible via a single model API. Our ‘Fugu Ultra’ model matches the performance of Fable and Mythos, delivering frontier capability without the risk of export controls. Try it: sakana.ai/fugu 🐡
English
Mi retweetledi
Mi retweetledi

Ini ada kasus vibe coder dilaporin ke polisi 😂
> ada bisnis owner minta dibikinin website
> dapet harga murah IDR 3juta, ternyata yg ngerjain vibe coder
> setelah website jadi ada security issue dan kena hack. si owner mengalami kerugian sampai IDR 10juta lebih
> owner komplain ke yg bikin website, malah WhatsApp-nya diblock
> owner mau laporin si vibe coder ke polisi
Tadinya mau hemat malah jadinya boncos wkwk


Indonesia




























