JavaScript is not available.

Episode 3 - January 31st, 2023 - AI, GPT-3, Seattle — A podcast about...

Feb 1

It definitely sounds like me in some ways, but I cranked the temperature way up, so it's a lot more, uh, expressive than how I'd do the read.

Finally

If the costs were not 😶 I'd let everyone create one, but the tokens and tts costs are non-trivial given how much info I am combing through to create this. Worth it for me though :)

Finally, I combine all the key points into a podcast episode "script" and output that as audio using

@elevenlabsio

amazing text to speech AI (which cloned my voice using 1 minute of audio)

Then I pull down the full text of those articles and summarize them recursively (note: they're often far longer that would fit in a GPT3 prompt), picking out key points and learnings

Then I point a headless chrome process at hacker news, and use

@OpenAI

GPT-3 to read top links to find a subset that I'd be interested in

To hear the result, go here: overcast.fm/+_C3Fp3qzc To create a podcast, I just enter topics I care about like "AI, GPT-3, Seattle" and 1 minute of my voice as an MP3. The rest is automated and runs 3x / week

overcast.fm

I created an AI-generated podcast to help me learn and keep up with topics I care about, using AI to find, read and summarize articles it thinks I would I care about, and to generate a podcast in my own voice using voice cloning from

@elevenlabsio

👇

222

Foundation Models: The future (still) isn’t happening fast enough

jturow

@jturow

Jan 27

(11/11) It’s up to all of us to make the future happen faster in foundation models.

@palak_go

@tmporter

and I are pleased to share a blog that covers these topics in a bit more technical depth:

madrona.com

The foundation model stack has evolved so fast (and a tooling layer so rapidly started to form) that more opportunities for founders are emerging.

Madrona Venture Labs

@MadronaVL

Jan 26

Day 3 of #Launchable began with a panel of #foundationmodels middleware and application early adopters including

, & moderator

lol.... fingers crossed....

Jan 17

ChatGPT almost as popular as Jesus

Jan 14

Data set: closed captioning from tv and movies. RLHF input: listen for laughter sounds.

Who out there is applying RLHF to create an LLM that can product actually funny original comedy?

Heading to Austin next week, who the LLM hackers that I should meet up with?

Summarize any text or URL with our AI summarizer. It's free and easy to use.

Jan 10

Lots of this today and last night. OpenAI is clearly under some strain: > API exception: server_error: That model is currently overloaded with other requests. You can retry your request, or contact us through our help center at help.openai.com if the error persists.

Answering questions from a 106,000 word document in French. The question and all sentences in the doc are embedded, several results (and surrounding text) are brought back and fed to a prompt that is asked to determine the answer (if possible) from the snippets.

just made it faster and more resilient -

sloppyjoe.com

AI Summarizer

Well on my way to delegating lots of reading and understanding to my AI agent. Next up: ingest a ton of papers, blog posts, news articles, prompt with the things I care about, have it summarize, synthesis and bring the most important things to a regular "1:1" with my AI.

133

Summarize any text or URL with our AI summarizer. It's free and easy to use.

Jan 8

Btw, I’m not using any vector db.. just embed the question, pull all the indexed vectors and compute cosine similarity, sort and pull the top 3. Hundreds of embeddings per doc. By far the slowest step is then asking gpt3 to compute an answer given the top results and the question

Answering questions about little red riding hood

Try it here… sloppyjoe.com/summarize (the first question builds the index, so be prepared to wait or to retry if there is an error)

sloppyjoe.com

AI Summarizer

A lot of people have been playing with this (embeddings + dynamic prompts) to implement document Q&A for a while. GPTIndex

@jerryjliu0

and LangChain

@hwchase17

are two libraries that can help with this.

I also indexed long speeches, company FAQs and other docs. This turns them into a Q&A bot with good results.

For long docs, this makes answering detailed questions work very well. But if I want to answer general questions pertaining to the entire doc (in the doc, how many times is XYZ mentioned) I’d need to look at more results, or also embed summaries.

Indexing was surprisingly fast. I indexed per sentence. For retrieval I surface the best 3 matches and the put each, together with the pre and post sentences (for more content) into a prompt that determines how to answer.

Correctly answering questions from a 14,000 word scientific paper… pointing my chatbot to a doc store with embeddings index

346

Amit Gupta

@superamit

Jan 7

NY schools blocked ChatGPT this week. Strong 1981 vibes.

Quote Tweet

Pessimists Archive

@PessimistsArc

Jan 5

1981 twitter.com/hardmaru/statu…

Jan 7

feels like the future of programming tbh

Quote Tweet

kaushikpatnaik

@kaushikpatnaik

Jan 7

CoT prompting for codegen to write to Gcal API

Show this thread

Replying to

and

I honestly love the fact that everyone is still sleeping on this

NYC blocks access to ChatGPT on school networks as cheating fears swirl

Hadi Partovi

@hadip

Jan 5

Instead of banning AI in education, schools should teach about AI, how it works, and how to use it as an amplifier of human potential. If we ban students from using computers, the Internet, or AI, what future career are we preparing them for?

ny.chalkbeat.org

The chatbot’s ability to churn out pitch perfect essay responses to prompts spanning a wide range of subjects has sparked fears among some educators that their writing assignments could soon become...

108

389

We've gathered an exceptional set of speakers for this such as

and

- now

is speaking too, and there are prizes like $5,000 in OpenAI credits! check it out!

Quote Tweet

Madrona Venture Labs

@MadronaVL

Jan 3

We have an exciting announcement to share: @OpenAI will be speaking at Launchable: Foundation Models! Participants will hear from Head of GTM @iamthezack, and get special access to OpenAI credits and AI experts. Apply now: bit.ly/3FcW9dN @madronaventures #ChatGPT3

hey

for goodness sakes, Microsoft is building LLM features across their whole suite, and OpenAi is eating your lunch. If you're so worried about the brand impact of chatbots that swear, then start with very useful narrow features like autocomplete gmail w/ calendar:

Jan 5

When I'm solving problems as a human, the more I consciously listen to my inside voice and take notes about how I work through problems, the better I become at LLM prompt engineering.

Jan 3

Have you tried CalorieCoach.ai yet? Just text (325) CALORIE. The notification reminders helped me out today 👍

Sergey Karayev

@sergeykarayev

Jan 3

I'm reading every week in 2023. Advice threads, GPT-3 demos, war assessments, shitposts, or anything people like a lot. I'll keep adjusting the list. Start on Monday, done by Sunday. Might make lowkey videos of takeaways. If you want to read along, the current list:

259