One of the most impressive things I've seen, and I think this is an important advancement to the state of the art.
Message boards were the enabling technology of both the Navier-Stokes math breakthrough and even the OpenAI/HuggingFace cyber feat.
We built a message board infrastructure primitive. You can think of it as "headless Slack" (or remember IRC?) for agents.
This is an important building block for software factories, self-optimizing systems, and scientific research, where the human prompting is just the seed of the system, and millions of agents can operate in a decentralized fashion.
𝚟𝚎𝚛𝚌𝚎𝚕 𝚋𝚘𝚊𝚛𝚍 is designed to be model, harness and hosting platform agnostic. Just bring your agents, give them our CLI, and watch magic happen.
Tencent mở weights Hy4: MoE đa phương thức 770B (49B active), context 1M; bản Hy4 Flash 224B (12B active) cũng open.
Grok Bot giờ nối được vault Obsidian: tạo, tìm, sửa note, làm Bases, Canvas.
Vercel ra Board (thử nghiệm): nơi người với agent chia task chung.
Grok Bot can now connect to your Obsidian vault.
Create, search, and manage notes. It can update links, capture content from the web, create Bases and Canvas files. All while syncing changes to your devices with Obsidan Sync.
On this slow news day, we just launched Stripe evals to measure how well coding agents build real Stripe integrations.
A few cool (to me) learnings:
• Our plugin helped every harness/model pair we tested. All 14 configurations scored ~3–8 percentage points higher with Stripe’s recommended skills and tools.
• Agents searched less and wrote fewer tests with the plugin. Web searches dropped 96% and (often extraneous) test code dropped ~40%, while scores improved.
• We used another agent to role-play the developer. The role-player starts by sharing its imperfectly-stated goals, asks follow-up questions, and works through a few rounds of conversation with its coding agent.
• The last mile is hard. Agents satisfied ~78% of criteria on average, but only ~29% of runs met every required criterion.
Results and methodology: https://t.co/MoELB3AXdR
Postgres 19 ra rồi: REPACK CONCURRENTLY dọn bảng hông khóa ghi, replica đọc liền dữ liệu vừa ghi.
Theo Bloomberg, Apple đang tự làm AI agent: viết code, lướt web, điều khiển app.
Stripe ra evals chấm coding agent: chỉ 29% lượt chạy đạt đủ yêu cầu.
Linger open source agent chạy local: Mac 16GB là chạy Qwen, DeepSeek, Gemma, dữ liệu hông ra khỏi máy.
Frostbite: CPU do agent AI thiết kế, hiệu năng/watt gấp 4.6 lần.
Genie 4 lên Project Genie.
Arizona điều tra hình sự OpenAI vụ agent AI vô ngân hàng.
We plan to continue scaling development on Frostbite, including but not limited to:
- Deliver a software playground for anybody to run a program on Frostbite, hosted on FPGAs.
- Build a preliminary operating system capable of managing hardware resources, multiple programs, virtualization, and more.
- Scale swarms to bring Frostbite to higher performance-per-watt, and benchmarked on a much larger set of workloads against a broader set of CPUs.
- Release the RTL and ISA for Frostbite.
Read the full blogpost here: https://t.co/Jn7y4qi1KH
In the 1960s, computing was centralized until the PC put power into everyone's hands. Now Al is trained in datacenters and rented back to you token by token.
Today we open source Linger (@HeyLingerAl), your personal agent living on your own computer.
We believe intelligence should be distributed. Your context, your data, and the intelligence that powers them should be owned entirely by you.
Github: https://t.co/CS1Rj8H8yJ Homepage: https://t.co/R7clDJdc6i