Staff Engineer @ Google Recommendation Systems Professor @ Columbia University
Joined November 2017
- Tweets 403
- Following 89
- Followers 763
- Likes 77
39 Photos and videos
27 Jan 2024
OpenAIs new embedding seems to really prefer earlier text. Cos(emb(t1), emb(t1 t2)) > Cos(emb(t1), emb(t2 t1)) ~97% of the time of the 1000 examples I tried. Interesting retrieval consideration
1
1
320
27 Jan 2024
This holds true for Cos(emb(t2), emb(t1 t2)) < cos(emb(t2), emb(t2 t1)) as well. So the second string doesn’t matter.
248
29 Nov 2023
With an A100 you can already get this down to ~250ms for 1 iteration
28 Nov 2023
Introducing SDXL Turbo: A real-time text-to-image generation model.
SDXL Turbo achieves state-of-the-art performance with a new distillation technology, enabling single-step image generation with unprecedented quality, reducing the required step count from 50 to just one.
The code, research paper, and weights for non-commercial use are now available on our website.
You can test SDXL Turbo on Stability AI’s image editing platform @Clipdropapp, with a beta demonstration of the real-time text-to-image generation capabilities.
Learn more: stability.ai/news/stability-…
1
1
331
27 Nov 2023
I wonder if sampling of these tokens is the same as others? I’d imagine you want to be greedier with tools so it hallucinates less?
24 Nov 2023
It emits special words, e.g. <|BROWSE|> etc. When the code "above" the LLM detects these words it captures the output that follows, sends it off to a tool, comes back with the result and continues the generation. How does the LLM know to emit these special words? Finetuning datasets "teach" it how and when to browse, by example. And/or the instructions for tool use can also be automatically placed in the context window (in the “system message”).
1
216
6 Jul 2023
161
17 Jun 2023
What errors/mistakes/hallucinations happen 1 in 100, 1000, 10k and so on? Going to be a whole net set of outages over the next couple years
Caught gpt-4-0613 hallucinating a json value for the first time (invalid, per the schema I gave it)
Ran it for ~20 times without issue. That's a ~5% error rate.
Cool that we get JSON, but must be validated and rerun. We are still wrestling a beast we can't quite control.
1
286
14 Jun 2023
From my testing, 3.5 gets very confused if the function has a bug in it. Example of write/read to file, read file return random contents. it'll keep trying. 3.5 & 4 are convinced that it needs to re-write instead of re-read. It trusts us too much.
GPT-4 and GPT-3.5 Turbo models in the API now support calling your custom functions, allowing the model to use tools you design for it. Also — reduced pricing & new model versions (including 16k context for 3.5 Turbo): openai.com/blog/function-cal…
1
204
5 Apr 2023
GPT4 scored 86 percentile on march madness bracket, better than 8/10 of your friends/colleagues
1
4
359
5 Apr 2023
15 Mar 2023
Had Sydney/#ChatGPT/#gpt4 create a #MarchMadness bracket: @ZagMBB you are the AI's favorite, good luck. Included are reasons why it thinks Gonzaga will beat @UA_Athletics. CC @MarchMadnessMBB
play.ncaa.com/mens-bracket-c…
151
25 Mar 2023
I use TikTok and IG almost exclusively for food and parenting content. My feeds are usually pretty identical between the two. This week I’m getting a ton of pro TT anti-Congress content even as I continue to scroll past them.
171
23 Mar 2023
Does @OpenAI or the users pay Wolfram?
Who is paying for these plugins? Will OpenAI add some token system? A more interconnected “App Store”? The AI chooses which plug-in to use if multiple options are given?
23 Mar 2023
2.5 months later...in collaboration with @openAI , ChatGPT gets its "Wolfram superpowers"!
writings.stephenwolfram.com/…
ALT Diagram showing January cover for bringing computational knowledge superpowers to chatGPT then an arrow to the new Wolfram plugin for ChatGPT over an image of the plugin working inside ChatGPT for an example of Jupiter's moons complete with accurate data and visualizations.
3
2,436
17 Mar 2023
15 Mar 2023
Had Sydney/#ChatGPT/#gpt4 create a #MarchMadness bracket: @ZagMBB you are the AI's favorite, good luck. Included are reasons why it thinks Gonzaga will beat @UA_Athletics. CC @MarchMadnessMBB
play.ncaa.com/mens-bracket-c…
157
15 Mar 2023
Had Sydney/#ChatGPT/#gpt4 create a #MarchMadness bracket: @ZagMBB you are the AI's favorite, good luck. Included are reasons why it thinks Gonzaga will beat @UA_Athletics. CC @MarchMadnessMBB
play.ncaa.com/mens-bracket-c…
1
571
15 Mar 2023
Sometimes cooperative, sometimes not, as well as different formats. And yes I did the entire bracket manually
96