Loading activity…
@weaviatepodcast
Follow for updates on the Weaviate Podcast!
AI
The show's announcement says UC Berkeley researchers explore generating task queues, databases and inference engines for specific workloads.
AI
Weaviate Podcast describes a clip on how softmax sums across context tokens, potentially making relevant documents harder to spot.
AI
The Weaviate Podcast’s host says guest Alex Ledbetter uses agents in Delegance Brokerage’s product and operations. He says Ledbetter shipped 900 PRs in three months with 18 terminal agents running.
AI
The Weaviate Podcast's host says the goal isn't a more human-sounding assistant, but a model of behavior that includes pushback, confusion and frustration.
AI
Weaviate Podcast highlights a mattress-search example: “Purple” can be a brand or a color, and it says an LLM plus an aggregation over the underlying data can settle the meaning.
AI
Weaviate Podcast says LightOn built retrieval models small enough to index a codebase locally on a laptop, then paired them with regex and file filters in ColGrep.
AI
Weaviate Podcast describes Mathew Jacob's finding and explores a sliding-window reranking approach that it says stayed robust at 1,000 documents.
AI
Weaviate Podcast describes questions built backward from short, verifiable answers, with four or five clues that search agents must check one search at a time.
AI
An author of “Querying Databases with Function Calling” says models often choose LIKE or exact text matching for natural-language commands that require SEARCH.
AI
Weaviate Podcast describes a benchmark built by Shreya Shankar and colleagues with 54 queries spanning 12 datasets and four database systems, testing how AI agents answer questions across databases.
AI
The podcast says co-founders Bob van Luijt and Etienne Dilocker went a year without paying themselves and raised a $1.2 million seed round during COVID.
AI
YC says it gathered researchers and founders to explore AI harnesses—the software around models—and lessons from building an agent for every employee at the company.
AI
A post sharing a Weaviate Podcast episode says the key lesson was giving an analysis agent tools to investigate why relevant documents ranked poorly, rather than relying on a score alone.
AI
Weaviate Podcast episode explores AI agent terminology with researcher Alex Zhang.
AI
Weaviate Podcast episode features Alex Zhang on agent behavior.
AI
Alex Zhang discusses limits of a Recursive Language Models paper on Weaviate Podcast.
AI
Weaviate Podcast tweet flags growing trust costs when agents run code.
AI
Weaviate Podcast post notes Alex Zhang's view on agent tool use.
AI
Hugging Face engineer describes sPTC parsing and pre-launching tool calls during streaming.
AI
Weaviate Podcast episode notes Claude Code fans out sub-agents with fixed programs
