OpenAI reduces Codex Model Context Size from 372k to 272k(github.com)
323 points by AmazingTurtle | 152 comments
A merged GitHub pull request in openai/codex backporting refreshed bundled model metadata (models.json) to the 0.144 release branch.
#context-window on Hacker News
11 stories tagged context-window, newest first.
Grok 4.3(docs.x.ai)
348 points by simianwords | 460 comments
xAI developer documentation page for the grok-4.3 model, listing modalities, a 1,000,000-token context window, pricing, and capabilities.
1M context is now generally available for Opus 4.6 and Sonnet 4.6(claude.com)
1157 points by meetpateltech | 493 comments
Anthropic blog post announcing that the 1M-token context window is generally available for Claude Opus 4.6 and Sonnet 4.6.
MCP server that reduces Claude Code context consumption by 98%(mksg.lu)
524 points by mksglu | 100 comments
Blog post introducing Context Mode, an open-source MCP server that sits between Claude Code and tool outputs to cut context window consumption by about 98%.
Claude Sonnet 4 now supports 1M tokens of context(anthropic.com)
1264 points by adocomplete | 668 comments
Anthropic product announcement that Claude Sonnet 4 now supports a 1 million token context window.
12-factor Agents: Patterns of reliable LLM applications(github.com)
388 points by dhorthy | 57 comments
GitHub repository by HumanLayer documenting twelve principles for building reliable, production-grade LLM-powered agent applications, modeled on 12 Factor Apps.
GPT-4o's Memory Breakthrough – Needle in a Needlestack(nian.llmonpy.ai)
430 points by parrt | 193 comments
Page introducing Needle in a Needlestack (NIAN), a benchmark testing LLM attention over long contexts of limericks, showing GPT-4o's strong results versus GPT-4 Turbo and Claude-3.
Claude 2.1(anthropic.com)
492 points by technics256 | 297 comments
Anthropic's announcement post introducing Claude 2.1, a new version of its Claude large language model, dated November 21, 2023.
MemGPT – LLMs with self-editing memory for unbounded context(github.com)
327 points by shishirpatil | 78 comments
GitHub repository for MemGPT, an open-source project that gives LLMs self-editing memory management to handle unbounded context.
The Secret Sauce behind 100K context window in LLMs: all tricks in one place(blog.gopenai.com)
406 points by T-A | 92 comments
A Medium blog post explaining techniques for speeding up large language models and enabling context windows of 100K tokens.
100K Context Windows(anthropic.com)
853 points by samwillis | 364 comments
Anthropic announcement from May 11, 2023 introducing 100K token context windows for its Claude language model.