Observations Using LLMs Every Day for Two Months
Tomasz TunguzVenture Capitalist If you were forwarded this newsletter, and you'd like to receive it in the future, subscribe here. Observations Using LLMs Every Day for Two Months
I’ve been using large-language models (LLMs) most days for the past few months for three major use cases : data analysis, writing code, & web search1. Here’s what I’ve observed: First, coding incrementally works better than describing a full task all at once. Second, coding LLMs struggle to solve problems of their own creation, turning in circles, & debugging can require significant work. Third, LLMs could replace search engines if their indexes contain more recent or evergreen data for summarization searches but not for exhaustive ones. Let me share some examples : This weekend, I wanted to clean up some HTML image links in older blog posts & modernize them to markdown format. That requires uploading images to Cloudinary’s image hosting service & using the new link. I typed this description into ChatGPT. See the transcript here :
The script failed to update the files. Subsequent iterations don’t solve the issue. The engine becomes “blind” to the error & reformulates the solution with a similar fundamental error with each regeneration. But, if I guide the computer through each step in a program, as I did for the recent Nvidia analysis, the engine succeeds in both accurately formatting the data & writing a function to replicate the analysis for other metrics.2 For web search, I created a little script to open chatGPT for search instead of Google each time I type in a query. Typing in queries feels very much like using Google for the first time on the high school library’s computer : I’m iterating through different query syntaxes to yield the best result. The summarization techniques often produce formulaic content. On a recent rainy day, I asked what to do in San Francisco, Palo Alto, & San Jose. Each of the responses contained a local museum, shopping, & a spa recommendation. Search results MadLibs! The challenge is that these “search results pages” don’t reveal how extensive the search was : how many of the TripAdvisor top 20 recommendations were consulted? Might a rarer indoor activity like rock climbing be of interest? There’s a user-experience - even a new product opportunity - in solving that problem. Recency matters : ChatGPT is trained on web data through 2021, which turns out to be a significant issue because I often search for newer pages. An entire generation of web3 companies doesn’t yet exist in the minds of many LLMs. So, I query Google Bard instead. These early rough edges are to be expected. Early search engines, including Google, also required specialized inputs/prompts & suffered from lesser quality results in different categories. With so many brilliant people working in this domain, new solutions will certainly address these early challenges. 1 I’ve written about using LLMs for image generation in a post called Rabbits on Firetrucks. & my impressions there remain the same : it’s great for consumer use cases but hard to drive the precision needed for B2B applications. 2 To analyze the NVDA data set, I use comments - which start with # - to tell the computer how to clean up a data frame before plotting it. Once achieved, I tell the computer to create a function to do the same called make_long()1.
|
Key phrases
Older messages
The Publicly Traded Company Worth 250x More in 10 Years
Thursday, May 25, 2023
Tomasz Tunguz Venture Capitalist If you were forwarded this newsletter, and you'd like to receive it in the future, subscribe here. The Publicly Traded Company Worth 250x More in 10 Years Ten
High-Flying SaaS Startups' Surge Won't Change the Valuations in Ventureland
Monday, May 22, 2023
Tomasz Tunguz Venture Capitalist If you were forwarded this newsletter, and you'd like to receive it in the future, subscribe here. High-Flying SaaS Startups' Surge Won't Change the
High-Flying SaaS Startups' Surge Won't Change the Valuation in Ventureland
Monday, May 22, 2023
Tomasz Tunguz Venture Capitalist If you were forwarded this newsletter, and you'd like to receive it in the future, subscribe here. High-Flying SaaS Startups' Surge Won't Change the
How Should You Staff Your Startup in 2023
Wednesday, May 17, 2023
Tomasz Tunguz Venture Capitalist If you were forwarded this newsletter, and you'd like to receive it in the future, subscribe here. How Should You Staff Your Startup in 2023 Yesterday, the
Which AI Model Should You Pick for Your Startup?
Tuesday, May 16, 2023
Tomasz Tunguz Venture Capitalist If you were forwarded this newsletter, and you'd like to receive it in the future, subscribe here. Which AI Model Should You Pick for Your Startup? A product
You Might Also Like
DocSend’s Advanced Data Rooms are here
Saturday, May 4, 2024
Pitch, analyze, and close deals in one intuitive platform View in browser Dropbox DocSend The Startup Index We've officially launched DocSend Advanced Data Rooms. Learn how it streamlines the
🔄 $8K MRR - 1 Founder - 0 employees - $0 marketing spend
Saturday, May 4, 2024
+ A note to "perfectionists"
🗞 What's New: Craft email campaigns that drive results
Saturday, May 4, 2024
Also: Mental health for founders!
What’s 🔥 in Enterprise IT/VC #392
Saturday, May 4, 2024
Raising a Series A is the hardest it's been in over 4 years but the Series B crunch is also coming - what to do when you're stuck... ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏ ͏
Almost went bankrupt
Saturday, May 4, 2024
Well... A lot of people don't know this about me, but in the early 2000s, I owned a snowboard shop in Alberta called the Real Deal. It almost bankrupted me. I just published a video where I tell
🚀 Lockheed Drops Terran Bid
Friday, May 3, 2024
Plus SES acquires Intelsat, Astroscale eyes IPO, $SPIR secures multi-million dollar deal and more! The latest space investing news and updates. View this email in your browser The Space Scoop Week
10words: Top picks from this week
Friday, May 3, 2024
Today's projects: JustSERP • MyArchitectAI • Fix My Speakers • Quizgecko • Airparser • ThoughtLeaders • GPT for Workspace • i Ask AI • Raguie • SaaS Dives • Language Atlas • AI Collection 10words
Descrb
Friday, May 3, 2024
Take photo, get product description, and many more BetaList BetaList Daily Descrb Take photo, get product description, and many more Too much email in your life? Switch to weekly emails or stop
🚀 Ready player one
Friday, May 3, 2024
Prepare to leave your 9-5 Dear , Ever watched "Ready Player One"? In that world, success in the OASIS hinges on knowing the game better than anyone else, mastering the clues, and leveraging a
Podscan, 2 months and $1k MRR in — The Bootstrapped Founder 317
Friday, May 3, 2024
2 months in. $1k MRR. And quite a few learnings.