The Promise and Pitfalls of Chaining Large Language Models for Email
Tomasz TunguzVenture Capitalist If you were forwarded this newsletter, and you'd like to receive it in the future, subscribe here. The Promise and Pitfalls of Chaining Large Language Models for Email
Over the last few weeks I’ve been experimenting with chaining together large language models. I dictate emails & blog posts often. Recently, I started using Whisper for drafting emails and documents. (Initially there were some issues with memory management, but I’ve since found a compiled version that works well on my Mac called whisper.cpp) After tying Google’s Duet I wondered if I could replicate something similar. I’ve been chaining the Whisper dictation model together with LLaMA 2 model from Facebook. When drafting an email, I can dictate a response to LLaMA 2, which will then generate a reply using the context from my original email. So far it works sometimes, but there are some clear limitations: First, the default tone of the generated emails is far too formal. [Link to example] Second, if I prompt LLaMA 2 to use a more casual tone, it often goes too far in the other direction. The problem is a lack of nuanced context - the appropriate level of familiarity varies greatly between emails to close colleagues versus board communications or potential investors. Without that nuance labeled and incorporated into the training data, it’s hard for the model to strike the right tone. Third, in multi-party email threads things can get confusing. If Lauren introduces Rafa to me, then Rafa bccs Lauren on the email, LlaMA 2 often replies as Lauren. Fourth, figuring out exactly the right settings for the model can be tough. Sometimes I dictate long emails, in which case the context windows (how much the computer listens to before transcribing) should be very long so the system can remember what I’ve said previously. Other times I’m just returning a very fast email. A quick see you soon or thank you very much. In which case a long context window doesn’t make sense and I’m left waiting for the system to process. I’m wondering whether small errors in the first model compound in the second model. Bad data from the transcription -> inaccurate prompt to the LLM -> incorrect output. I’m loo Overall the potential is exciting, but there are still challenges around tone, context, and multi-party interactions that need to be addressed before this can become a seamless productivity tool. Tn machine learning systems, achieving an 80% solution is pretty rapid. The marginal 15% - the magic behind ML - takes a huge amount of effort, data, & tuning. |
Older messages
SaaS Competitive Advantage Through Elegant LLM Feedback Mechanisms
Tuesday, October 3, 2023
Tomasz Tunguz Venture Capitalist If you were forwarded this newsletter, and you'd like to receive it in the future, subscribe here. SaaS Competitive Advantage Through Elegant LLM Feedback
Centaurs & Cyborgs : The Jagged Frontier of AI
Monday, October 2, 2023
Tomasz Tunguz Venture Capitalist If you were forwarded this newsletter, and you'd like to receive it in the future, subscribe here. Centaurs & Cyborgs : The Jagged Frontier of AI Last week,
Artisanal Emails
Wednesday, September 27, 2023
Tomasz Tunguz Venture Capitalist If you were forwarded this newsletter, and you'd like to receive it in the future, subscribe here. Artisanal Emails Artisanal chocolate, artisanal candles,
Avoiding the PLG Trap : Office Hours with Oliver Jay
Monday, September 25, 2023
Tomasz Tunguz Venture Capitalist If you were forwarded this newsletter, and you'd like to receive it in the future, subscribe here. Avoiding the PLG Trap : Office Hours with Oliver Jay On
Building Applications with AI - Lessons from LangChain, Hearth, & Context.ai
Thursday, September 21, 2023
Tomasz Tunguz Venture Capitalist If you were forwarded this newsletter, and you'd like to receive it in the future, subscribe here. Building Applications with AI - Lessons from LangChain, Hearth,
You Might Also Like
[CEI] Chrome Extension Ideas #171
Tuesday, December 24, 2024
ideas for Amazon, Podcast, Twitter, and AI ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
Top angel investors in the U.S.
Tuesday, December 24, 2024
Inspiration for who to raise from when you're raising your early rounds ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
🎁 🎄 HO HO HO! Here's the ultimate gift for your business journey
Tuesday, December 24, 2024
Unwrap your holiday gifts and start building your dream in 2025! fdrlogo Hey Friend , HO HO HO! Your holiday gifts have arrived! This isn't your typical holiday surprise—these gifts are proven
Biggest rounds of 2024
Tuesday, December 24, 2024
+ Sriram Krishnan joining Trump's government View in browser Sponsor Card - Up Round-35 Good morning there, Welcome to the last Sifted Daily newsletter of 2024, in which we look back on the biggest
The Corner Office & Low Exp 👩💼
Monday, December 23, 2024
And some holiday news͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
🗞 ICYMI: insights on o3, AI job disruption, marketing on Bluesky
Monday, December 23, 2024
Also: a new social network ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
top strategy research of 2024
Monday, December 23, 2024
every billion-dollar startup around the globe, tech that will change the world, and the strategy team playbook CB-Insights-Logo-light copy Our top strategy research of 2024 Highlights: Every billion-
🦄 Operating system for events
Monday, December 23, 2024
Flite streamlines and automates the event management process.
11 Silicon Valley Startups Raised $10.2 Billion - Week of December 23, 2024
Monday, December 23, 2024
🤓 AI's Biggest Annual Event: NeurIPS 💰 Predictions: US to Establish Bitcoin Reserve 💰 Bankless Crypto 2025 Predictions 🎮 Is Extended Reality (XR) Still Happening?💰 Tough Time for Non-AI Startups ͏
The Best Investing Advice
Monday, December 23, 2024
50 pieces of wisdom from some of the world's best investors ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏