Search: “context”

The AI research community released a set of notable papers between September 28 and October 4, highlighted in a weekly roundup. Key contributions include JAZ, CASD, Agensh, Jev‑Mem, AutoGym, Taste‑Ben

This post likely discusses how to prompt or configure an AI coding agent to incorporate unexpected or whimsical elements like goblins into its outputs, possibly as part of a broader discussion about A

Gary Marcus discusses concerns about generative AI's limitations and potential overhyping of the technology, arguing that initial enthusiasm may not translate into sustained practical breakthroughs as

Perplexity AI demonstrates a hybrid approach to AI inference that combines on-device processing for sensitive data with cloud-based AI services to achieve scalability and contextual understanding. Thi

Jeremy Howard comments on the Xiaomi MiMo v2.5 model, highlighting its exceptional value proposition and cost-effectiveness for prompt processing. The post appears to include comparative pricing data

This post likely discusses how meaningful work is enhanced and complemented by three key elements: the contextual environment in which work occurs, the specialized knowledge and skills brought to the

arXiv:2605.14855v1 Announce Type: cross Abstract: Forecasting within signal processing pipelines is crucial for mitigating delays, particularly in predicting the dynamic movements of objects such as N

Box announced its participation in Pinecone's Nexus launch, emphasizing that enterprise AI agents require contextual access to organizational data and content. The partnership highlights the integrati

We built a new way to train contextual embedding models, which encode each chunk of a document with the whole document in view. pplx-embed-v2-context-9b-preview sets a new state of the art on ConTEB a

Claude Code's session management capabilities and 1 million token context window are highlighted in this post, which references an official Anthropic blog entry. The feature allows developers to maint

Claude Code's session management features and 1 million token context window capabilities are now documented on the official Claude Blog. The post, shared by Thariq on X, covers how developers can lev

First AutoHarness, then AutoContext, now AutoCompact. I am seeing a rising trend of work that trains models to natively support more of what the harness does. This work specifically trains agents to d

a bunch here where I’m saying ok Garry’s kinda right?! 👀…in some ways :) we’re making this loop much easier to close out of the box soon If more people get into evals & traces to ground self-improving

Memory makes your agent smarter over time. The agent harness is key to the memory layer. You can't bolt one onto the other after the fact. Every decision the harness makes - what goes in context, what

This is the right frame. We’re currently designing our agent memory platform, and the hardest part isn’t storage — it’s deciding what to remember, when to retrieve, and how to keep context clean. All

For once I actually agree with the constructive argument here. There are more approaches that allow you to own your own destiny. Memory is just context after all and you can provide that at many place

Nice paper to improve inference efficiency. It's been a while we haven't seen good work on efficiency. Here is why it matters: A long-running agent's workspace outgrows its context window long before

Qwen3.8-Max is live on Together AI. Together AI is with us as a Day 0 launch partner, and we couldn’t ask for a better name to share Day 0 with. 2.4T parameters, 95B active, 1M context — all together

This is awesome and makes things much more composable. Love it deepagents now supports structured output for subagents! an under appreciated piece of context engineering is figuring out what context i

I like this framing a lot: agent improvement is harness improvement, not model improvement The interesting interventions are often at the tool boundary: - what context you pass - when tools are provid

Companion to the Qwen 3.8 Release Megathread. Compiled from ~2,000 posts scanned across both subs, with deep reads of the 45 highest-signal threads (560 posts and comments), Aug 15–22, 2026, plus inde

If you maintain an AGENTS.md or a CLAUDE.md, this is worth a read. (bookmark it) 288 gold-test evaluated runs across Claude Code and Codex, 17 real tasks from 3 repositories, with context-injection st

Highlights: 👉 SOTA coding—93.5% LiveCodeBench, Codeforces 3206, and 80.6% SWE-Bench Verified 👉 Hybrid attention efficiency—27% FLOPs and 10% KV cache vs V3.2 for long-context inference 👉 Three reasoni

Banger paper from Google DeepMind and colleagues. (bookmark it) A model reads its entire KV cache on every generated token, even though it ends up attending to a tiny slice of it. In other words, if y

Sometimes you need to start over. But that decision is hard. @llama_index had to make that call: they built one of the most popular AI frameworks in the world, but saw the agent harness and frontier l

A workflow audit is no longer the best way to figure out how to use AI in your job. Despite the advice from AI labs, I'm more convinced, because of AI's reasoning capabilities and long context horizon

Nous Research announced that their Hermes Agent now includes an integrated MCP (Model Context Protocol) Catalog, enabling users to discover and access available Model Context Protocol tools and integr

toodles from mickey mouse clubhouse was weirdly ahead of its time wake phrase: mickey mouse clubhouse launched in 2006, and “oh toodles” trained toddlers on the assistant wake phrase years before siri

the Codex x @skybysoftware acquisition may have been one of the best @openai deals made in the last year. I've been waiting for 'real' computer use since @romainhuet demoed the ChatGPT App with 4o Vis

Harrison Chase, co-founder of LangChain, wrote a post in a similar style to a piece by Sarah Wooders, focusing on the concept of 'your harness, your memory' in the context of AI agents and memory syst

Banger paper from Microsoft and colleagues. If you run agents that search a large document collection, this one is worth your time. (bookmark it) They introduce CorpusMap, which resolves recurring ent

Natural language can act as an in-context control surface that streams rich, constrained UI and links users into deeper web views.

This is all I will say on the matter: It’s alarming to see the constant effort to try to tell me how I should use AI, how I should build AI, and now how I should pace it. Is it just me, or are all the

My conversation with @jerryjliu0. He's building @llama_index: document infrastructure for AI agents, the layer underneath everything models need to work. Did you know he's the guy whose tool half the

If you keep safety rules or coding standards in an AGENTS.md or a CLAUDE.md, this one is worth your time. (bookmark it) Researchers measured what context compaction actually destroys across 20 product

What a fascinating paper on AI agents. A lot of the issues we see with AI agents today revolve around wrong assumptions the LLMs make. This leads to problems like hallucination, cost inefficiencies, u

gave a talk 'owning your intelligence' - ty @sequoia @sonyatweetybird for having me talked about harnesses and evals and the role they play in owning your intelligence TLDR: > agents = model + harness

Open models give teams more room to run agent loops, with API prices at a fraction of GPT-5.6 Sol and Claude Fable 5. That matters as planning, tool calls, retries, and long contexts compound token us

what does the 'last human code review' look like? to @itamar_mar, ceo and founder of @QodoAI, it looks like two agents talking to each other, backed by a context engine specific to your organization.

In our new paper, EDGE-OPD (EviDence GuidEd On-Policy Distillation), we introduce two key ideas for improving On-Policy Distillation (OPD). First, we use guided rollouts that inject privileged context

// δ-mem: Efficient Online Memory for LLMs // One of the more elegant memory mechanisms I've seen this month. Most long-term memory work either inflates context or retrains the model. This paper shows

A lot of work around AI in 2023 was spent on building picks and shovels. I would know this because that was basically the core goal of the original @llama_index framework. Today, a lot of that is no l

langgraph persistence lets you checkpoint agent state at every step so you can pause, resume, and replay from any point. essential for long-running agents. docs: https://docs.langchain.com/oss/python/

without memory, ux with an agent is really bad memory is what makes an experience with an agent feel personal and optimized i'm doing a bunch of research re how folks are building memory into their ag

The referenced tweet (status ID 2042696610614849548) is not publicly accessible via search, and the X.com URL requires JavaScript/login to render. Based on the available context from related search...

let me introduce you to the langchain stack 1. langgraph gives you this level of control 2. traces give you the complete run lineage 3. version your skills and instructions in context hub 4 & 5. deepa