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

73

Your dot now has…

46.7

Hướng dẫn chatgpt

Your dot now has… ⚡️ Faster replies 💬 Less jargon 🫡 Better follow-through And, they can now follow your custom instructions. Tell your dot in the thread things like how to behave or which actions need your go-ahead. “always talk in lowercase.” “Show me a draft before sending any emails.” You can also set custom instructions and rules in Customize > Behavior on mobile, or through your dot’s menu on web and desktop. Media

X · 13 thg 11, 2026

Nguyên văn nguồn
Chi tiết nguồn
75

"My Grok Bot advisor talked me out of a $1.35M mistake" - @Rasmic

46.3

Hướng dẫn gregisenberg

Người viết chia sẻ cách thiết lập “Advisor” trong Grok Bot. Họ đề xuất tạo bot, tìm “finance” trong plugins và kết nối qua Plaid, rồi đưa mục tiêu trong năm, giao một nhiệm vụ là ngăn người dùng đưa ra quyết định sai. Trước mỗi thay đổi lớn, hãy gửi chi tiết và hỏi “wdyt of this”.

X · 12 thg 11, 2026

Biên tập tiếng Việt
Chi tiết nguồn

"My Grok Bot advisor talked me out of a $1.35M mistake" - @Rasmic Here’s how to set up your own advisor Grok Bot: 1. Create a new bot in Grok Bot and name it Advisor 2. Search “finance” in plugins and connect your accounts through Plaid 3. Tell it your goals for the year: what you’re saving for and what you’re building 4. Give it one job: “Stop me from making bad decisions. Be blunt.” 5. Before any big move, send it the details and ask “wdyt of this.” A purchase, an investment, an acquisition, a new business idea. Media

  • Here’s how to set up your own advisor Grok Bot:
  • Before any big move, send it the details and ask “wdyt of this.”
  • 1. Create a new bot in Grok Bot and name it Advisor
  • 2. Search “finance” in plugins and connect your accounts through Plaid
76

In reasoning model development, it's always been this interesting tension between training/optimizing chain-of-thoughts (CoTs) vs not touching them to preserve monitorability.

46.2

Hướng dẫn rasbt

In reasoning model development, it's always been this interesting tension between training/optimizing chain-of-thoughts (CoTs) vs not touching them to preserve monitorability. CoTs are cool because we can check what the model is up to (e.g., whether it cheats or not) as long as it spells out its thought process. And we risk losing that if we explicitly optimize CoTs. Two caveats: 1) I.e., the catch of CoT and monitorability is that this only works if the written thinking reflects what the model is actually doing. 2) Also, when models become more capable, they spell out less in the CoT (like a cleverer math student needs less note-taking when solving problems during an exam). Nothing new on that front, but an interesting thread below on how to measure "harder to monitor", with some interesting results that confirm the existing intuitions: 1) no-CoT capability (meaning how much reasoning the model can do in a single forward pass without writing anything down) - Better pretraining (lower perplexity) raises this no-CoT capability - Architecture mostly doesn't matter 2) CoT controllability (meaning how well the model can change its written reasoning when asked to add, remove, or change parts of it) - RL alone raises controllability a lot - Controllability is passed on through distillation * Higher no-CoT capability and higher controllability both make monitoring harder. PS: Perhaps the good news is that it seems that process supervision wasn't the main culprit.

X · 12 thg 11, 2026

Nguyên văn nguồn
Chi tiết nguồn
77

Super interesting work on agent memory.

46.2

Hướng dẫn omarsar0

Super interesting work on agent memory. (this is a must-read) It discusses whether agents can manage their own memory. If so, what would that self-organized memory look like? This is the closest implementation that I have seen to my own memory system. I mostly use linked documents with my agents, and it has been working extremely well. It works well because frontier models have gotten better at persisting external knowledge. The problem: Memory systems usually fix the schema in advance, with set record types and rules for how to group them. The solution: SoMem gives the agent ordinary linked documents instead. The agent decides what to summarize, which topics to create, and when to revise them. Every summary links back to the original interaction as evidence, and the runtime builds time, relation, and recency views on top. At question time, the agent chooses what to search and follows links to the source when it needs to check. SoMem beat the strongest baseline by 2.66 points on LoCoMo, 3.10 on BEAM-100K, and 2.00 on LongMemEval-S. Memory built by one model also worked when read by another. If your agent already reads and writes files, try letting it organize memory as linked notes before adding a vector store. https://arxiv.org/abs/2611.11929 Chat with Paper: https://academy.dair.ai/papers/can-llm-agents-organize-their-own-memory-2611.11929

X · 12 thg 11, 2026

Nguyên văn nguồn
Chi tiết nguồn
78

We're almost one week out from Thesis and the attendance survey results are in:

45.3

Hướng dẫn bran_don_gell

We're almost one week out from Thesis and the attendance survey results are in: Every’s first annual conference has an NPS of 71.4 with 76% percent of attendees saying that they are returning next year regardless of ticket price or speaker lineup. A 71 NPS is considered world-class or elite performance. This is incredible, not only because Thesis was @every's first ever conference, but because we executed on it with a team of four people—none of which had event experience. Some things I’m particularly proud of that we pulled off: • We built what I think (and what I’ve heard) was the coolest digital experience for a conference. We just updated it so the schedule now links directly to the recorded livestream. You can watch all the sessions here → http://every.to/tv • We knew community was important, but we didn’t expect how important. 70% of attendees said it made the conference for them. No surprise, and now we’re doubling down on community… more to come on that soon. • We didn’t use a single piece of over-the-counter event software to run the conference. I looked at all of them (and have experienced many of them). They’re generic, bulky, and impossible to customize. They aren’t Every. So we took a few existing pieces of software that we had built ourselves and turned them into an event management system that our team could continually improve as needed. The result was that everything digital that an attendee touched was bespoke, thoughtful and customized for them. Checkout how beautiful the schedule is → https://every.to/thesis-2027/schedule. This really paid off, 96% of attendees rated the digital experience as excellent. • The little details of the conference were endless, from the curated bookshop that every attendee could take from to the goodie bag to the 48 hour WhatsApp group to the open office hours. Every single thing was thought through. • We held 25 highly curated and thoughtful sessions across 8 hours in 3 different stages. The coordination was flawless and to our surprise, we need to double the size of the Classroom next year. We knew people would be interested in how we pulled this off, so we literally held a session called "How to Run a Conference with Agents and Notion" in our classroom. We walk step by step through how we validated the idea, brainstormed the event, organized it, managed it, and ultimately executed on it. • I personally burned 3,000,000,0000 tokens managing the event through codex. • Our team used the @every agent (http://every.to/agent) 935 times to work collaboratively across every facet of the event, all inside slack. The team at notion took everything we did and turned it into a template that anyone can use to run their own conference, complete with the prompts we used → https://www.notion.com/templates/event-planner-every @DABrundage @poojary_yash @darustudio and @reijowrites, @itsbdell, and @katelaurielee were the big guns behind Thesis. They absolutely killed it. We learned so many important things and had a blast while putting it on. If you attended, THANK YOU. See you at Thesis: 2028!

X · 12 thg 11, 2026

Nguyên văn nguồn
Chi tiết nguồn
73–78 / 179
Trang 13 / 30