AI & machine learning2023 · shared on Hacker News
Lost in the Middle: How Language Models Use Long Contexts (2023)
Explore Lost in the Middle: How Language Models Use Long Contexts (2023), its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Comment #49097604 Comment #48972984 Comment #44790474 Comment #40979069 Comment #40136103 Comment #38796364 Comment #38205479 Comment #38167089 Comment #38132180 Comment #38070106 Comment #37908727 Comment #37511906 Comment #37302776 Comment #37178033 Comment #37034052 Comment #36991722 Comment #36918462 Comment #36760270
Ytosh ·
Codestral Mamba
485 points138 comments
Yaraghuvanshi ·
LLMs and the Harry Potter problem
65 points61 comments
Ygzer0 ·
GPT-4 Update: 32K Context Window Now for All Users
53 points26 comments
YspIrr ·
Handbook.md shows that long policy documents do not reliably govern agents
45 points19 comments
Yxinweihe ·
Show HN: TraceRoot – Open-source agentic debugging for distributed services
40 points22 comments
Ygk1 ·
You probably don’t need to fine-tune LLMs
16 points0 comments
Ydavidbarker ·
Introducing ChatGPT Enterprise
10 points5 comments
Ywilliamzeng0 ·
Launch HN: Sweep (YC S23) – A bot to create simple PRs in your codebase
9 points1 comments
Yja3k ·
Benchmarking GPT-4 Turbo – A Cautionary Tale
9 points0 comments
Yshishirpatil ·
MemGPT – LLMs with self-editing memory for unbounded context
6 points0 comments
Ybobvanluijt ·
Explainer Video – Lost in the Middle: How Language Models Use Long Context
4 points3 comments
Yaverylamp ·
Llama 32K Context Released by Together AI
3 points0 comments
Ykevin_hu ·
New models and developer products announced at OpenAI DevDay
3 points0 comments
Yrobertnishihara ·
A Comprehensive Guide for Building Rag-Based LLM Applications
2 points0 comments
YHeidaradar ·
Microsoft says GPT 3.5 has 20B parameters?
2 points0 comments
Ystuhlmueller ·
Build a search engine, not a vector DB
2 points0 comments
Ywslh ·
Lost in the Middle: How Language Models Use Long Contexts (2023)
2 points0 comments
Ygk1 ·
Lost in the Middle: How Language Models Use Long Contexts
1 points0 comments
Yjojodoi ·
Language models use long contexts
1 points0 comments
Yandrewon ·
What's new in Llama 2 and how to run it locally
1 points0 comments
YAmazingTurtle ·
OpenAI reduces Codex Model Context Size from 372k to 272k
1 points0 comments