Zander Pease

739 posts

Zander Pease banner
Zander Pease

Zander Pease

@ZanderPease

Building https://t.co/myndSceB3N, the GTM AI Agent Platform

New York, NY Katılım Mayıs 2011
267 Takip Edilen1.4K Takipçiler
Elad Gil
Elad Gil@eladgil·
Just realized USV analyst/associate program spawned not 1, but 3 awesome founder/CEOs - @jml_campbell - CEO of Tagomi, sold to Coinbase, @christinacaci - CEO of Vanta @thedanigrant - CEO of Jam 🔥🔥🔥🔥🔥🔥🔥
English
14
9
278
41K
Zander Pease retweetledi
Richard She
Richard She@Richard_She·
The long road to this paper began at UCSF, survived the disruptions of the pandemic, a lab move to MIT, and many more obstacles along the way. We are deeply proud of this work. 2/ sciencedirect.com/science/articl…
Richard She tweet media
English
1
14
49
6.2K
Toran Bruce Richards
Toran Bruce Richards@SigGravitas·
Has anyone implemented a tool that allows the user to easily chat with a GPT embedding of any book (or pdf input)? 🗣️📖 Akin to @mckaywrigley's embeddings projects (see below), but for any file. Seems like it would be a simple enough next step, and a very useful tool! github.com/mckaywrigley/w…
English
9
4
26
12.5K
Zander Pease
Zander Pease@ZanderPease·
- Hallucination on provided documents/context is a non-issue once customers test the product, assuming each query is limited in scope to a small number of documents. There is no reasonable support for "summarize these 100 proprietary documents" in today's LLM world.
English
0
0
2
376
Zander Pease
Zander Pease@ZanderPease·
- Consumers of documents are sometimes more excited about LLM tech than the document owners. Ex. sales teams would love access to a chatbot of their product roadmaps; the PMs are more cautious. - Users are surprisingly tolerant of slow chat response times.
English
1
0
2
424
Zander Pease
Zander Pease@ZanderPease·
3 months after soft launching trysentient.com we've learned a lot about early customer interest in LLMs. Here are some takeaways: - Customers are willing to pay for "traditional" SaaS features like user management, SSO, and automatic document syncing.
English
1
0
3
685
Zander Pease
Zander Pease@ZanderPease·
Sentient ingests documents from Google Drive, Notion, Confluence, etc. and has a web interface and Slack app. It's built using GPT-3 but will switch over to ChatGPT once that is API available. Here's the demo: #demo" target="_blank" rel="nofollow noopener">trysentient.com/#demo
English
3
0
25
2.9K
Zander Pease
Zander Pease@ZanderPease·
My thesis is that every company will soon have an AI “librarian” for its employees to interface with. As a PM I constantly had to answers questions that were already well-documented - I know my colleagues in HR, Sales, etc felt the same. Hoping Sentient can help!
English
2
1
31
3.7K
Zander Pease
Zander Pease@ZanderPease·
I built a chatbot for company documents. Ask questions about HR policies, product strategy, market positioning, and get immediate answers. Give it a whirl: trysentient.com
English
29
20
288
76.5K
Zander Pease retweetledi
Harrison Chase
Harrison Chase@hwchase17·
🚨Biggest @langchain drop yet🚨 ⚡️Dynamic, zero-shot composition of multiple chains Easily plug in different subchains (google, REPL, wikipedia, DBs) just by telling the router LLM (in English!) when and how to use them `pip install langchain==0.0.8` github.com/hwchase17/lang…
English
9
45
253
0
Zander Pease
Zander Pease@ZanderPease·
TL;DR: SAMs break current user interface dichotomy of GUIs for people / APIs for third parties, shifting control of how a user accesses a service from the company to the user.
English
0
0
1
0
Zander Pease
Zander Pease@ZanderPease·
Thoughts on how software action models will commoditize some platform companies: @zander-pease/software-action-models-will-commoditize-todays-platforms-c690b069dd61" target="_blank" rel="nofollow noopener">medium.com/@zander-pease/…
English
1
0
2
0
Zander Pease
Zander Pease@ZanderPease·
Why large ML models will go the way of cloud services offerings @zander-pease/ai-market-theses-c1b23231526a" target="_blank" rel="nofollow noopener">medium.com/@zander-pease/…
English
1
0
8
0