Ed Parsons retweeted
GPT-4o hot take:
• The speech synthesis is terrific, reminds me of Google Duplex (which never took off).
but
• If OpenAI had GPT-5, they have would shown it.
• They don’t have GPT-5 after 14 months of trying.
• The most important figure in the blogpost is attached below. And the most important thing about the figure is that 4o is not a lot different from Turbo, which is not hugely different from 4.
• Lots of quirky errors are already being reported, same as ever. (See e.g., examples from @RosenzweigJane and @benjaminjriley.)
• OpenAI has presumably pivoted to new features precisely because they don’t know how produce the kind of capability advance that the “exponential improvement” would have predicted.
• Most importantly, each day in which there is no GPT-5 level model–from OpenAI or any of their well-financed, well-motivated competitors—is evidence that we may have reached a phase of diminishing returns.
Ed Parsons retweeted
Best advice I ever got: think like a VC when looking for tech job.
It led me to joining Rippling ($11B+) before its Series A. It changed my life, so I built a free tool to help others.
We expect that each company listed on Prospect will grow at least 2X over the next 4 years:
Ed Parsons retweeted
Claude 2.1 (200K Tokens) - Pressure Testing Long Context Recall
We all love increasing context lengths - but what's performance like?
Anthropic reached out with early access to Claude 2.1 so I repeated the “needle in a haystack” analysis I did on GPT-4
Here's what I found:
Findings:
* At 200K tokens (nearly 470 pages), Claude 2.1 was able to recall facts at some document depths
* Facts at the very top and very bottom of the document were recalled with nearly 100% accuracy
* Facts positioned at the top of the document were recalled with less performance than the bottom (similar to GPT-4)
* Starting at ~90K tokens, performance of recall at the bottom of the document started to get increasingly worse
* Performance at low context lengths was not guaranteed
So what:
* Prompting Engineering Matters - It’s worth tinkering with your prompt and running A/B tests to measure retrieval accuracy
* No Guarantees - Your facts are not guaranteed to be retrieved. Don’t bake the assumption they will into your applications
* Less context = more accuracy - This is well know, but when possible reduce the amount of context you send to the models to increase its ability to recall
* Position Matters - Also well know, but facts placed at the very beginning and 2nd half of the document seem to be recalled better
Why run this test?:
* I’m a big fan of Anthropic! They are helping to push the bounds on LLM performance and creating powerful tools for the world
* As a practitioner of LLMs, it’s important to build an intuition for how they work, where they excel and their limits
* Tests like these, while not bulletproof, help showcase real world examples and get a feeling for how they work. The goal is to transfer this knowledge to productive use cases
Overview of the process:
* Use Paul Graham essays as ‘background’ tokens. With 218 essays it’s easy to get up to 200K tokens (repeated essays when necessary)
* Place a random statement within the document at various depths. Fact used: “The best thing to do in San Francisco is eat a sandwich and sit in Dolores Park on a sunny day.”
* Ask Claude 2.1 to answer this question only using the context provided
* Evaluate Claude 2.1s answer with GPT-4 using @langchain evals
* Rinse and repeat for 35x document depths between 0% (top of document) and 100% (bottom of document) (sigmoid distribution) and 35x context lengths (1K Tokens > 200K Tokens)
Next Steps To Take This Further:
* For rigor, one should do a key:value retrieval step. However for relatability I did a San Francisco line within PGs essays for clarity and practical relevance
* Repeat test multiple times for increased statistical significance
Notes:
* Amount Of Recall Matters - The model's performance is hypothesized to diminish when tasked with multiple fact retrievals or when engaging in synthetic reasoning steps
* Changing your prompt, question, fact to be retrieved and background context will impact performance
* The Anthropic team reached out and offered credits to repeat this test. They also offered prompt advice to maximize performance. It's important to clarify that their involvement was strictly logistical. The integrity and independence of the results were maintained, ensuring that the findings reflect my unbiased evaluation and are not influenced by their support.
* This test cost ~$1,016 for API calls ($8 per million tokens)
Ed Parsons retweeted
🚨 Big announcement!
We've made our first acquisition @HightouchData - workflow automation startup Workbase ⚡️
The Workbase team is all-star, and I couldn't be more proud to share that they've joined 🚀
Learn why in our interview on @Forbes by @fredsoda forbes.com/sites/frederickda…
Ed Parsons retweeted
Very excited to finally share what @richardfreling, @vinayyala, and I are working on
@CommandBar adds a magical "command k" widget to any web app
- Let users search to discover any feature
- Blazingly fast CLI for your power users
- De-bloat your UI
techcrunch.com/2021/08/09/co…
Ed Parsons retweeted
⭐️ ⭐️ ⭐️ ⭐️ ⭐️ ⭐️
#SixTimes
Ed Parsons retweeted
Getting ready to release some Ripley Templates that you can use with your team. Any suggestions for what you’d like to have us build out? Or, would you like to contribute a template? Let us know!
Ed Parsons retweeted
Ripley: The project management tool for G Suite producthunt.com/posts/ripley via @edparso
Ed Parsons retweeted
Ahh! We are featured on #BetaList! 🎉🎉🎉
Ripley: Team Project Management for Google Drive that doesn't drive you crazy nitter.cf/BetaList/status/105255… betalist.com/startups/ripley… via @BetaList
Ed Parsons retweeted
Life hack: When in bed, meditate. Either you will have a deep meditation, or fall asleep. Victory either way.
Ed Parsons retweeted
"If this ever becomes mainstream, the whole thing will come crashing down."
– top comment on the TechCrunch article on Airbnb, 2008
Ed Parsons retweeted
The best way to increase a startup's growth rate is to make the product so good people recommend it to their friends.
Ed Parsons retweeted
This is how self-driving cars would work at an intersection. nitter.cf/yugaishibuchi/status/6…
Ed Parsons retweeted
The most impressive people I know spent their time with their head down getting shit done for a long, long time.



















