Register and share your invite link to earn from video plays and referrals.

Search results for SharedContext
SharedContext community
One keyword maps to one global community path.
Create community
People
Not Found
Tweets including SharedContext
Glean is now multiplayer. One chat. Shared context. Your team creating, discussing, and reviewing work together. Meet team chat, now in open beta. Ask your admin to turn it on. 🎥
Show more
the worst part about having multiple codex accounts is the lack of shared context. the best part is that I'm literally building the perfect solution for that for years now :) It's like retardmaxxing with a mega swarm army of PHDs who just know me in and out
Show more
Your team. Your Agents. One shared context. Discuss, decide, and build together. See human–Agent collaboration in action with Qoder.
Engineering, Product, Marketing, each in its own silo, with its own context OpenClaw Multiplayer gives teams one shared agent and shared context, so they can actually work together @Pishgar on what we showed at GitHub Universe:
Show more
Stimulating piece on Scottish education in @asteriskmgzn: I suspect that discussions of canon, culture, and shared context to return to the fore in the coming years, as many skills, narrowly-construed, are ceded to AI, and as some of the excesses of de-Arnoldization, and the processes that Arendt described in her writing on education, start to recede. I’m curious on the causal linkage between PISA scores and the reforms he describes. It feels like a very exciting time to be a theorist of education, and I assume that the best work will come from surprising places.
Show more
BREAKING: Meta is taking Muse Code “out of beta” with paid plans, adding multi-agent workflows, shared context and a new SDK for building custom agents.
A useful but little-known Gemini API feature 💰 Sending the same massive system prompt with every request? That token bill adds up fast. Gemini's "Context Caching" lets you cache long, shared inputs once and reuse them across subsequent requests, dramatically cutting input token costs. If you're repeatedly working with large documents or lengthy prompts, this changes the economics entirely. 📌 Title: Context Caching 🔗 URL: 🧩 Overview Every time you send a long shared context (full manuals, codebases, hundreds of PDF pages) to an LLM, you pay for those tokens again. Context caching holds that context on Google's side so follow-up requests just reference it. There are two flavors: implicit caching (identical prefixes are automatically reused) and explicit caching (you manually create a cache with a TTL). 🛠 How to use it For explicit caching, call the cache creation API with your system instruction or large input content. You get back a cache name to pass into subsequent generateContent requests. TTL defaults to one hour and is adjustable. Implicit caching requires zero setup: identical input prefixes are reused automatically, so you may already be benefiting without any code changes. 🏗 Building it into production ・Internal knowledge-base QA: cache your full company manuals or policy docs so each user question doesn't re-send the entire corpus. Faster responses, lower cost. ・Code review bots: cache the repo's codebase and coding standards, then each PR review request skips re-uploading the common context. ・Customer support: cache FAQs and product specs so every ticket doesn't carry a massive context payload. ・Batch analysis pipelines: when running many individual queries against the same reference data, caching compresses the per-query cost. 💡 Use cases 📚 Repeated Q&A over long documents 🔍 High-volume requests sharing the same system prompt 🧑‍💻 Dev tools with an entire codebase as context 📊 Multi-angle analysis on a single dataset ⚠️ Watch out There's a minimum token count to create a cache, so short prompts won't qualify. Cache storage also has its own cost, which can outweigh savings if usage is infrequent. Match the TTL to your actual access pattern and focus on use cases where the same large context is genuinely hit many times. ✨ The cost of "sending the same thing over and over" compounds quickly. Start by caching your longest shared context and watch the bill drop. #Gemini# #LLM#
Show more
🎤 Walrus asked builders at Sui Live whether agent memory should travel with users across platforms and providers. Every answer was yes. Shared context across tools, fewer tokens burned re-explaining yourself, agents that pick up where the last one left off. Memory that lives wherever you signed up first isn't really yours. Data matters. So does who owns it.
Show more