Skip to content

Search stories, models, companies…Subscribe

Topic · Concept

Long context

Long context refers to a model's ability to take in very large inputs, now commonly a million tokens or more, in a single request. Bigger windows let a model read whole codebases or long documents at once, but a large window is not the same as reliable recall of everything in it.

11 stories · updated Oct 27

Follow via RSS Get Long context alerts

Key facts

Checked Oct 9

"Lost in the Middle" finding: Recall is often best at the start or end of the context (Liu et al., Jul 6, 2023)
Gemini 1.5 research claim: >99% retrieval up to at least 10M tokens (vendor research, Mar 8, 2024)
Gemini API: "Many Gemini models come with large context windows of 1 million or more tokens"
Claude API: 1M-token context on Fable 5.1, Opus 5.5, Sonnet 5.5, Haiku 5.5
Independent 2026 evaluation: ATLAS benchmark paper (May 27, 2026); covers earlier models such as Claude Opus 4.6 and Gemini 3.1 Pro Preview

Start here

Research · ExplainerContext windows vs memory vs RAG: what each one actually doesA 1M-token window, a chatbot that "remembers you" and a retrieval pipeline solve different problems. Here's how each works and when to use which.Oct 9·7 min read

Latest on Long context

Developers · ExplainerWhat is context engineering? How it differs from prompt engineering, and where the practice stands in October 2026What is context engineering? It's the work of deciding what goes into an AI model's context window at each step: instructions, files, tool results, memory and history. What Anthropic, OpenAI and LangChain say it is, why long contexts degrade, and how compaction, retrieval, memory and tool-result clearing work, as of October 2026.Oct 27·9 min read

Open source · NewsMeta Muse Spark Open: the 816B open-weight model, its Muse Model License and what it takes to runMeta released Muse Spark Open on October 15, 2026: an 816B-parameter (42B active) open-weight model with a 1M-token context, under a new Muse Model License. What the license actually allows, what hardware it needs, and how Meta's own benchmark table stacks up.Oct 16·6 min read

Open source · NewsNvidia Nemotron 3.5 Super VL and Bolt: open weights under OpenMDW, and what the Opus 5 comparison really showsNvidia released Nemotron 3.5 Super VL, a 120B-parameter (12B active) hybrid Mamba-Transformer model with a 1M-token context, and Nemotron 3.5 Bolt 74B-A9B on October 15, 2026, with a 4 GB Bolt E4B due October 23. The license is permissive; the headline wins over Claude Opus 5 and GPT-6.1 Sol come from customized versions on narrow tasks.Oct 16·6 min read

Models · NewsGemini 4 Argon is now generally available: price, who gets it and what Google claimsGoogle opened Gemini 4 Argon to paid API developers, AI Pro and Ultra subscribers and businesses on October 13, 2026. The Gemini 4 Argon price is $2/$10 per million tokens through November 30, then $4/$20, and free users are still left out.Oct 14·6 min read

Developers · GuideHow to use Gemini 4 Argon: in the Gemini app, AI Studio, the Gemini API and AntigravityHow to use Gemini 4 Argon depends on where you want it: AI Pro or Ultra for the Gemini app, Ultra for AI Studio's Playground and Antigravity, and a billing-enabled key for the API. Plans, steps from Google's docs, sample code, costs, limits and fixes.Oct 14·8 min read

Developers · ExplainerClaude Code's "Compacted while idle" message, explained: why it happens and how to turn it offSince about version 2.1.286, Claude Code can summarize a large conversation on its own shortly before its one-hour prompt cache expires. Why Anthropic does it, when it fires, what it costs you, and the one-line setting that stops it.Oct 12·9 min read

Open source · NewsDeepSeek-V4.1-Flash: an MIT-licensed open-weights MoE that DeepSeek says beats its own flagshipReleased September 10, DeepSeek's new Flash model activates 8B–16B parameters per token, reads 1M tokens and images, and now answers V4-Pro API calls. What's confirmed and what's vendor-reported.Oct 9·7 min read

Models · BenchmarksLong-context recall: what independent benchmarks say "1 million tokens" really buys youEvery frontier API now accepts about a million tokens. Independent evaluations from RULER to ATLAS show how much of that window models actually use.Oct 9·9 min read

Products · CompareChatGPT vs Gemini for research: deep research, long documents, prices and privacy comparedBoth now write cited research reports. The real differences are how much each plan can read at once, how they handle your PDFs, and what happens to your data.Oct 9·Checked Oct 9

Products · ExplainerHow Gemini handles a 900-page PDF: the limits, the costs and what long-context benchmarks showOn paper, a 900-page document fits comfortably in Gemini's 1M-token context. Whether it works depends on file size, your plan and what you ask.Oct 9·6 min read

Nothing in this format on this page — try another filter or the next page.