The LangChain Hub
Documentation of the LangChain Hub as a searchable repository of prompts for LLM developers, with investigation into when search functionality was added.
Posts
Filter by tag
hallucinationsocial-search-requestPerplexity-AIcomparing-resultsgenerative-searchprompt engineeringsearch-auditsmicro interactions in searchYou.comspeculative-designGoogle-BardCGTbetter-searchcompetition-in-searchchoice-in-searchgenerative-web-searchknowledge-cutoffsalternative-search-enginesevaluating-results-metasearch-quality-complaintsstanding-queriessearch-engine-optimizationrepository-of-examplesAnthropic-ClaudeCFP-RFPRAGPhinddoubtingadvertising-in-searchseo-for-social-goodOpenAI-ChatGPTpublic-interest-technologyspeculative-classroom-exercisesTavilysearch-user-interfacesgenerative-search-APIfresh-searchautocomplete-in-web-searchfalse-premiseTikTokAndievaluating-search-enginesarticulationsocial-searchdata-poisoningInflection-AI-Piacademic-searchChainForgeautomation biasMeno-Paradox+221 more
I am wary of over-indulging in prompts and missing...
the impetus to search... spaces that reward curiosity... ways to distribute evaluation
[Xrvgu Heona "frpbaq nyohz"]
Trying to 'find the grounding' and finding flipping and waffling.
Planning CSUIRx
Comparative Search User Integration Rx - Recipe / Reception / Research / Review
standing-queries?
Reflection on documenting persistent research questions that warrant better answers but aren't urgent enough to pursue immediately.
unsealing knowledge
What can and will we do to unseal knowledges?
"Scheherazade, you easily make up stories of Egypt or any country you please."
Analysis of AI hallucination behavior by testing a Plato quote completion task across multiple LLM systems (ChatGPT, Claude, Bard, Pi, Perplexity, YouChat).
Bug log
Technical documentation of website bugs including pagination issues with sort:date searches and incorrect back-to labels for pposts.
searchsmart.org
Overview of searchsmart.org's approach to testing academic search systems using metamorphic testing from the user perspective.
"We really need to talk more about monitoring search quality for public interest topics."
- Dave Guarino (Jan 16th, 2020)
SUI External Feedback & Complaints Log
A doc listing feedback on complaints re search user interfaces (SUI).
My first attempt at using ChainForge
The briefest introduction.
The Need for ChainForge-like Tools in Evaluating Generative Web Search Platforms
A provocation.
retrieval-augmented generation (RAG)
What is retrieval-augmented generation (RAG)?
TIL to use raw triple double quotes for doctests with escapes
On some struggles with chatbots and gensearch tools.
"custom instructions" in Siri
What might that look like?
"The robot is not, in my opinion, a skip."
Weblink to a Twitter thread arguing that physical automation shouldn't be dismissed as just another passing tech trend like crypto or metaverse.
Microsoft CFP: "Accelerate Foundation Models Research"
"...essential to realizing the promise of AI to benefit people and society while mitigating risks"
You can still search [dic] when "less is more"
A minor bug report on a search user interface.
public health inspection signs as potential search seeds
Could take a photo of a sign and be led directly to the inspection report?