Rivaldo Silalahi(Bang Dou) retweeted
The TiDB leaks
fulcrumsec.vg/pingcap/
Rivaldo Silalahi(Bang Dou) retweeted
You said we're doing nothing? Dude, we're doing everything we can for this country. Even when our voices and concerns are constantly ignored, we still speak up
RAKYAT BERSATU, TAK BISA DIKALAHKAN 🇮🇩✊🏻
📍Tugu Tani, Jakarta — 20 Oktober 2026
Rivaldo Silalahi(Bang Dou) retweeted
Welcome to Como, @ManUtd! 🔵
Founded in 1878, Manchester United are one of the most historic clubs in English football. Known as the Red Devils, the club have built a rich tradition across domestic and European competitions, with 20 English league titles, 13 FA Cups and three European Cups to their name.
Rivaldo Silalahi(Bang Dou) retweeted
SEE WHAT YOU HAVE DONE, DUDE!
illustrated by: @serabutannn
Rivaldo Silalahi(Bang Dou) retweeted
DocumentDB 1.0 is now generally available. An MIT-licensed, MongoDB-compatible document database built on PostgreSQL, DocumentDB lets you run existing MongoDB workloads on a familiar Postgres foundation.
Find more details on the 1.0 GA release here: documentdb.io/blogs/posts/do…
Rivaldo Silalahi(Bang Dou) retweeted
🚨 PiG 0.5.0 is out 🐷
This release took a while, and I am very happy with it. Version 0.5.0 covers all of Pi's interfaces on Pi 1.3.0. Out performs PiG 0.4.1 in every measurement. Piglets can now change PiG itself and you choose how lean PiG is.
pi-in-go.dev
Rivaldo Silalahi(Bang Dou) retweeted
Kata Asa josjis bolo
#BABYMONSTER #ASA
Rivaldo Silalahi(Bang Dou) retweeted
Source is out: github.com/VictorTaelin/Unii…
I've been using Unii as my only agent for a month, and I couldn't be happier. I'm free from the torture of /compact, AGENTS.md, managing Claude sessions, and I can't overstate how empowering that is.
I also keep receiving enthusiastic DMs of people who forked it to do their own thing, but I'm concerned that your AIs might get some tricky parts wrong, like caching and the exponentially decaying logs. So, please, ask it to study my codebase and fix anything that might be wrong in yours. I just want to make sure you get the right experience, because it is actually magical.
People have ported it to OpenCode, Pi, and many other harnesses. If you did so, feel free to post it below.
Also check UniiChat.com for my exact version!
My harness: UniiChat.com
This is the closest to infinite context I've experienced.
I've been using it for a week to organize my life and build things (including itself!), and it just keeps going. I only use it now.
OSS next week, prompt to build your own below ↓
Rivaldo Silalahi(Bang Dou) retweeted
Mercury 3 is live: the most capable diffusion LLM released to date.
It outperforms GPT-6 Luna and Claude Haiku 5.5 across a range of benchmarks while running at over 1,000 tokens per second.
More than 40x the size of Mercury 1, 3x more intelligent across standard benchmarks, and just as fast, with a 1M-token context window.
Available today on the Inception API, @baseten, and @OpenRouter .
Rivaldo Silalahi(Bang Dou) retweeted
We trained our Muse foundational models, including Muse Wonder, at Prometheus, our gigawatt-scale supercluster in New Albany, Ohio.
Across a supercluster with hundreds of thousands of GPUs, even one underperforming host can slow an entire training run. We engineered Prometheus for resilience at scale, achieving 85%+ goodput on pretraining, 90%+ on reinforcement learning and ~47K GPU hours mean time between interruptions during Muse Wonder training.
Take a look at the tech powering Prometheus: go.meta.me/4yXXApZ
Rivaldo Silalahi(Bang Dou) retweeted
1/ Introducing the Cua Spaces SDK.
Every big lab now ships a bot with its own computer: Grok Bot, Muse, dots. None let you bring your own. With Cua Spaces, now you can.
Put Claude Code, Codex or any agent on compute you choose, and run jobs across all your computers at once.
my second contribution to @opentelemetry 🥳
github.com/open-telemetry/op…
Rivaldo Silalahi(Bang Dou) retweeted
MiniMax M3.1 Flash: Space Performance + Bunny Speed
🚀🐰 Yes, Space Bunny - which has topped global leaderboards with 200T+ tokens - was an earlier version of M3.1 Flash.
💰Redefining the performance economics of agentic AI. M3.1 Flash achieves frontier-level intelligence across key tasks such as Cowork (Automation-Bench: 62%; ALE: 30%), Coding (DeepSWE: 74%) and Visual Reasoning (BabyVision: 91%), at 1/3 the cost of M3 and 3x the speed.
API pricing (flat rate): $0.15 / $0.60 per 1M input/output tokens, with cache reads at $0.015 / 1M tokens.
Model weights will arrive on Oct 23.
API: platform.minimax.io
M Plan: minimax.io/m-plan
MiniMax Code for desktop: agent.minimax.io/download
