AllyshipContent Radar

Hands-on 278

Công cụ, thử nghiệm và hướng dẫn thực hành

Crawl live-1795090500000 · 19:15 19 thg 11, 2026 · Xuất bản 19:35 19 thg 11, 2026

25

ok, so one thing stand clearly between with working hermes (@NousResearch ) vs Rex (@superlogical) or @herdrdev

58.2

Hướng dẫn luongnv89

ok, so one thing stand clearly between with working hermes (@NousResearch ) vs Rex (@superlogical) or @herdrdev it is also the BIG different between working with AI bots vs working with an AI Agent > you do not PROMPT directly to the worker Agents. you can just say what you want, then the AI Bots will write a prompt and send to the worker Agents and frankly, at least in my case, they write much better prompt than me. yes, of course you can do almost the same in Rex, or Herder, but each time you open a new window/ or reset a session, it is a new session, and you could be back to square-1 when you have to explain to the main agent how to work yes, you can setup an environment where your main agent can "automatically" update memory to know how you want it to work, but it is not come natural as you work with AI Bots and yes, AI Bots is an AI Agent at core,

X · 18 thg 11, 2026

Nguyên văn nguồn
Chi tiết nguồn
28

Grateful for another trip around the sun today with the best family, friends and founders/coworkers ✌️

57.2

Hướng dẫn nikunj

Grateful for another trip around the sun today with the best family, friends and founders/coworkers ✌️ Life’s been chaotically busy with just work, computer, family and some sleep. Not much time for anything else. Goal for next year is to do all of those, get fit, be present and be funmaxxing as much as possible. Send me your best tips on how to do it all!

X · 18 thg 11, 2026

Nguyên văn nguồn
Chi tiết nguồn
29

GPT-6.2 Astra 🧠, Microsoft’s seven models 🚀, Replit Missions 🤖

57.0

Hướng dẫn TLDR

Get Delinea's 2026 Identity Security Report to learn why standing privilege is creeping back into mature identity programs and how agents become over-permissioned. See the full data and learn how to extend control from the point of access to the moment of action.

TLDR AI · 18 thg 11, 2026

Nguyên văn nguồn
Chi tiết nguồn
30

Highly recommended read.

56.8

Hướng dẫn omarsar0

Highly recommended read. Self-improving memory is starting to look like an important component for continual-learning agents. So pay close attention to this research direction if you are studying recursive self-improvement. Just last week, I featured a few papers on the topic, and this week both Meta and Google published on it. (find more references towards the end) Meta lets a model design its own memory habits. Then they train those habits into the model weights. The goal is to allow the system to learn the memory design (what to memorize, how to memorize, and what to recall). This work is actually in the same vein as RIME, which I wrote some notes on last week: https://x.com/omarsar0/status/2121335666457944226 Meta first searches for better memory instructions (prompts the model to rewrite itself), then fine-tunes the model (SFT with LoRA) on runs that used the best ones. RIME, on the other hand, skips the search and uses RL to train one model to solve tasks and write memories, rewarding notes that help on later tasks. It also trains the model to explore so it collects useful information. Different ways to address the problem. More useful links below: Google Self-Improving Memory for Continual Learning - https://x.com/omarsar0/status/2122701047118635485 How to Train Memory Writing for Continual Learning - https://x.com/omarsar0/status/2121335666457944226 Can LLM Agents Organize Their Own Memory - https://x.com/omarsar0/status/2120888604402815485 Continual-ARC - https://x.com/omarsar0/status/2120638750740844672 Adaptive Memory Selection for LLM Agents - https://x.com/omarsar0/status/2118715786152001580 MemCredit - https://x.com/omarsar0/status/2121610612040220832

X · 18 thg 11, 2026

Nguyên văn nguồn
Chi tiết nguồn
25–30 / 179
Trang 5 / 30