Research agents built for depth over speed @ycombinator S23
San Francisco, CA
Joined July 2023
- Tweets63
- Following3
- Followers320
- Likes128
Webhound retweeted
This is a fantastic product for truly deep research, substantially better than just Codex + Parallel/Exa. Extremely comprehensive results. I highly recommend checking them out.
Agents are lazy at research. They stop at the first confident answer, even when more research could change it.
Webhound is your agent’s research engine. You use budget to decide how much research a question deserves.
We gave it $5 to investigate a border wall contract. It found an unreported $18M change.
Webhound retweeted
We've been ramble-coding for months at Webhound, so I wrote this up on some things we've learned from using dictation apps to prompt agent
One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.
Webhound retweeted
As a “business guy” I’m slightly embarrassed to share what I’ve been vibe coding. I’ve built a pipeline for doing deep research on San Francisco public policy issues using Manus, Webhound.ai, and Dropbox. When I share I hope you all will have a ton of useful advice (instead of flaming me).
Webhound retweeted
A lot of people asking "why webhound?"
As one of the founders here's why imo
