60 stories tagged with #context, in publish-time order across the WeSearch catalog. Tag pages update as new stories ingest.
⌘ RSS feed for this tag → or search "Context"
Running a 35B LLM at 128K Context, Full Speed, on €870 of Used Hardware
How a €870 used-GPU box runs a 35B model at full speed all the way to 128K context — and what I learned measuring the upgrade, including……
Coding Agents Don’t Need Bigger Context Windows — They Need a Context Compiler
Most coding agents treat prompt construction like retrieval: gather more files, add more context, hope the model figures it out. But that approach breaks down fast. As context grow…
Stateless MCP has recaptured my interest (and inspired mcp-explorer and datasette-mcp)
Tuesday was Stateless MCP day - the rollout of MCP 2.0, or the 2026-07-28 Model Context Protocol specification to use the more formal but less memorable name. This is the most sign…
Contextor-spare LLM tokens required for full structural analysis of Python repo
Contextor transforms complex Python repositories into structured architectural context that both developers and Large Language Models (LLMs) can understand. It generates JSON repor…
212k AI coding benchmarks: context beats generic prompts
Updated June 2026. This guide was originally based on 1,458 Python benchmarks. Since then, we’ve run 212,000+ benchmarks across Python, Go, JavaScript, and C#—testing chain-of-thou…
Pennant Knowledge Engineering Studio – Compile Graph Context for AI Agents
Knowledge Engineering Studio. Contribute to galeluka/Pennant development by creating an account on GitHub.…
Microsoft is reportedly fixing the really slow Windows 11 context menu, and we can customise it too
There's a good chance the rumor is true.…
How to Build a Context Layer and a Company Brain
What it actually takes to turn a company's scattered knowledge into something an LLM can reliably use — and why the demo is 5% of the work.…
Show HN: Memsprout – share AI context with your teammates
memsprout quickstart: connect your team's agents to one shared memory in under 5 minutes — connect an MCP client, create a Space, invite a teammate, capture a Memory, and watch the…
Malloy semantic modeling lang gets 'Credible' backing to build out AI context
Context, not correlation, will define successful AI implementation
Why contextual AI underpins successful autonomous AI adoption…
Lightweight, zero-dependency prompt that prevents AI agents from losing context
The two-document pattern for AI agents: an immutable, append-only log for reasoning and refutations (DESIGN.md), and an edited-in-place index for current rules (CLAUDE.md). - PROMP…
LFM2.5-Encoders for Fast Long-Context Inference on CPU
A Blog post by Liquid AI on Hugging Face…
Show HN: Segue – Save context in one AI, load it in another by a short handle
Save context in one AI, get a short handle, load it in another. No copy-paste, no re-explaining.…
Show HN: Directed Memory Bank – Tool-agnostic project context for AI agents
Stop re-explaining your project every AI session. Tool-agnostic project context in plain markdown — works with Claude Code, Cursor, Codex, Gemini, any agent that reads files. - pmi…
Show HN: Ctxdiff – Git diff for your LLM agent's context window
git diff for your agent's context window. See exactly what your LLM saw — turn by turn, block by block. - salmanzafar949/ctxdiff…
Australia news live: comedian who hosted Albanese’s ‘shag, marry, date’ interview says it was ‘moment taken out of context’
Follow the day’s news live Get our breaking news email , free app or daily news podcast What you need to know about today’s AusAlert test It’s also well worth watching this video o…
Show HN: Health context/timeline for AI (mobile app)
Download Kurozu: AI Health Context by YIFAN WU on the App Store. See screenshots, ratings and reviews, user tips, and more apps like Kurozu: AI Health Context.…
AI-Generated Mental Health Advice Misjudged Due To Differences In Stateless Versus Contextual Evaluations
Evaluations of AI dispensing mental health advice are often done in a manner that is radically different from real world usage. I showcase this. An AI Insider scoop.…
The new rules of context engineering for Claude 5 generation models
We removed over 80% of Claude Code's system prompt for more advanced models. How to apply the lessons we learned to your own context engineering in Claude Code and with your own ag…
Tarun Tahiliani’s secret isn’t embroidery. It’s context
Explore Tarun Tahiliani's immersive fashion experience at Navaratna, redefining couture through storytelling and cultural context at India Couture Week.…
Show HN: Protoai – an open source peer-to-peer network for sharing AI contexts
A peer-to-peer network for sharing AI contexts. Contribute to johndebord/protoai development by creating an account on GitHub.…
LeBron James leaving Lakers for 76ers makes sense within context of winning
When LeBron James decided to leave the Lakers, immediate questions swirled about what he’d prioritize in his unprecedented 24th NBA season (and possibly beyond).…
Community context shapes corporate response to violence in street protests
Context Windows Forget What Matters — I Built a Usage-Reinforced Decay Engine for AI Agent Memory
Most AI memory systems keep the newest information—not the most important. Here's how I used the Ebbinghaus forgetting curve to build a better memory engine for LLMs. The post Cont…
Show HN: Elpis – a Rust TUI for LLM agents with context pruning
You put an agent into an Elpis, and it becomes Elpis; Be Elpis my friend. - MasihMoafi/Elpis…
Founders OS – open-source MCP server that gives AI your business context
Open-source MCP tools that give your AI the full context of your business. CRM, finances, memory, tasks, and news - all in one connection.…
LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning
arXiv:2607.19358v1 Announce Type: new Abstract: Recent advances in long chain-of-thought reasoning models such as DeepSeek-R1 have led to increasingly longer inference context leng…
Prompt Engineering Isn’t Enough: How Four Bricks of Context Engineering Stop RAG Hallucinations
Enterprise Document Intelligence [Vol.1 #9bis] - Your RAG isn’t hallucinating, it’s answering the wrong context faithfully. On real NIST and World Bank documents, watch each of the…
Show HN: A Chrome extension for LeetCode with context-aware hints and mock in
Surgical DevOps – Prevent LLM context drift and regressions
core-methodologies. Contribute to bonushora/surgical-dev-ops development by creating an account on GitHub.…
Beyond grep: The case for a context-rich AI coding harness
Augment Code's Vinay Perneti talks models, harnesses, and context.…
OpenAI’s Codex context reduction for GPT 5.6 sparks dissatisfaction among developers - InfoWorld
OpenAI’s Codex context reduction for GPT 5.6 sparks dissatisfaction among developers InfoWorld…
The context layer for AI: Bringing trusted Dropbox content into OpenAI workflows - WebWire
The context layer for AI: Bringing trusted Dropbox content into OpenAI workflows WebWire…
Researchers detail "context bombing", where defenders use prompt injections to trigger guardrails of attackers' LLMs, cutting AI hacking success rates by ~90% (Dan Goodin/Ars Technica)
Dan Goodin / Ars Technica : Researchers detail “context bombing”, where defenders use prompt injections to trigger guardrails of attackers' LLMs, cutting AI hacking success rates b…
Quantum Logic as the Logic of Contexts
Quantum logic is usually presented as a non-classical departure from ordinary reasoning forced on us by quantum mechanics, with classical logic kept as the secure starting point. W…
Correlation-Aware Contextual Bandits with Surrogate Rewards for LLM Routing
We study contextual bandit problems with correlated arms and access to surrogate reward signals produced by a machine learning model, motivated by applications such as large langua…
Minimal Decision Dynamics and Contextual Probability: A Quantum Tug-of-War Model
Decision making often exhibits context dependence that challenges classical probability theory. This paper develops a quantum-like extension of the Tug-of-War (QTOW) decision-makin…
Fictional Worldbuilding: Multi-Agent LLM Collaboration with Hierarchical Context Compression and Iterative Review
arXiv:2607.09403v1 Announce Type: new Abstract: Worldbuilding, the construction of coherent fictional worlds, is a foundational task in game design and literary creation. Large Lan…
Scoped Verification for Reliable Long-Horizon Agentic Context Evolution under Distribution Shift
arXiv:2607.09175v1 Announce Type: new Abstract: Deployed LLM agents rely on agentic context, the model-external textual control content assembled by an operational harness. In this…
Email inboxes for AI agents: the complete guide – MailKite
Why an autonomous agent needs a real inbox — to receive verification codes, hold email threads, and act as a participant instead of a script. The two architectures (bring-your-own …
Long Context vs. Short Context Model: When Does a Long Context Model Win?
Balancing context capability against cost, speed, and data The post Long Context vs. Short Context Model: When Does a Long Context Model Win? appeared first on Towards Data Science…
Preserving Context When Moving from ChatGPT to Codex CLI
A lot of useful technical work starts as a conversation. Maybe you are exploring an architecture...…
At AWS Summit, AWS announced Continuum, which uses AI to find and fix code vulnerabilities, Context, which organizes company data for AI agents, and more (Todd Bishop/GeekWire)
Todd Bishop / GeekWire : At AWS Summit, AWS announced Continuum, which uses AI to find and fix code vulnerabilities, Context, which organizes company data for AI agents, and more —…
Tyra Banks Sues Netflix Over ‘America’s Next Top Model’ Documentary, Claims Interview Was “Stripped of Context”
Banks claims the streamer edited her interview into a story she never told.…
Jedify raises $24M to help companies arm AI agents with context on their business
The funding round was led by Norwest, with participation from S Capital VC, Cerca Partners, and Oceans Ventures. Snowflake Ventures also participated as a strategic investor.…
ContextLogic director Paul S. Levy purchases $232,343 in shares
Looking for people to test common AI context window across GEMINI, ChatGPT, Claude, and Perplexity
Something has changed. More memory. More context. More coherence. Curious if others are noticing it too!
Breaking the "Ass-Kissing" Loop: How Context Saturation and Multi-Model Accountability Disrupted Factory Guardrails [R]
Prompt Engineering Is Table Stakes. Context Engineering Is the Next Frontier.
Prompt Engineering Is Table Stakes. Context Engineering Is the Next Frontier. Salesforce...…
I'm trying to build a "living memory/context engine" for my business. Help me architect it.
I'm trying to build a "living memory/context engine" for my business. Help me architect it.
Alibaba releases Qwen3.7-Plus, a multimodal proprietary model with a 1M-token context window, costing $2 per 1M tokens, 60% less than text-only Qwen3.7-Max (Carl Franzen/VentureBeat)
MiniMax M3 is out: 1M context, open weights coming soon, 83.5 BrowseComp against Claude Opus 4.7's 79.3
Context Graph Agent
CGA (ContextGraphAgent) is a local-first graph context service for AI-assisted development. - nascousa/cga…
Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing
AI-assisted coding agents are bottlenecked by input-token cost. Two pathologies of raw human input drive much of this overhead: tokenization inefficiency for non-English text and s…
CP-Agent: Context-Aware Multimodal Reasoning for Cellular Morphological Profiling under Chemical Perturbations
Cell Painting combines multiplexed fluorescent staining, high-content imaging, and quantitative analysis to generate high-dimensional phenotypic readouts to support diverse downstr…
InfoMem: Training Long-Context Memory Agents with Answer-Conditioned Information Gain
Long-context tasks require LLMs to identify and preserve answer-relevant information from large contexts. Chunk-wise memory agents address this issue by sequentially reading docume…
Fitting WhisperX large-v3 + a 24B LLM on one 3090: a reproducible context-capping recipe
This is the technical, reproducible version of a fix I shipped on my own homelab. If you want the...…