Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
swyx Profile picture
@swyx
Mar 23, 2023 • 8 tweets • 6 min read • Read on X
Scrolly
ChatGPT casually dropped an APP STORE 🤯

It can now:
- browse the web (RIP Bing waitlist, cutoff)
- write and run Python (RIP replit?)
- access org info (RIP docsearch startups)
- add third party plugins from OpenTable, Wolfram, Instacart, Zapier, etc)
- developer SDK in preview
When I talked about the AI Red Wedding last year () I was talking about AI offerings undercutting existing human-based or manual business processes.

Now the AI Red Wedding is coming for companies building atop foundation model companies.

@OpenAI is… twitter.com/i/web/status/1…
@OpenAI Actually, calling it a "Developer SDK" is stretching it:

1. Define API with OpenAPI (heheh not to be confused with OpenAI)
2. Explain what the API is for and what the methods do.

that's it, no step 3. ChatGPT can figure out when and how to use it correctly now.

@karpathy… twitter.com/i/web/status/1… ImageImageImageImage
@OpenAI @karpathy IT RUNS FFMPEG.

CHATGPT RUNS FFMPEG.

I think people aren't properly appreciating it's ability to run -and execute- Python.
IT RUNS FFMPEG

IT RUNS FREAKING FFMPEG. inside CHATGPT.

CHATGPT IS AN AI COMPUTE PLATFORM NOW.

what. is. happening. ImageImage
twitter.com/i/spaces/1djGX…
946 people tuned in to an emergency unscheduled ChatGPT space lol

people are so hyped about this, it is unreal.

thanks to special guests @OfficialLoganK, @Altimor @dabit3 and the couple dozen others who joined in to revel in the biggest app store launch of the decade Image
CHATGPT IS READING AND SUMMARIZING MY REACTIONS TO CHATGPT THAT I MADE 2 HOURS AGO

hi chatgpt i love you please kill me last

Image
discussions on the latent.space discord live

discord.gg/EbgtDcqczg

join in!

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with swyx

swyx Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @swyx

swyx Profile picture
Apr 14
don't miss that OAI also published a prompting guide WITH RECEIPTS for GPT 4.1 specifically for those building agents... with a new recommendation for:

- telling the model to be persistent (+20%)
- dont self-inject/parse toolcalls (+2%)
- prompted planning (+4%)
- JSON BAD - use XML or arxiv 2406.13121 (GDM format)
- put instructions + user query at TOP -and- BOTTOM - bottom-only is VERY BAD
- no evidence that ALL CAPS or Bribes or Tips or threats to grandma workImage
Image
Image
Image
cookbook.openai.com/examples/gpt4-…
we're publishing our GPT 4.1 chat with @michpokrass later today pls like n sub youtube.com/@latentspacepod
Read 7 tweets
swyx Profile picture
Mar 30
.swyxrules for working on long running/expensive code:
Unbundle run() into:

- init()
- continue(id)
- cleanup(id)

never assume you will call these in order
Always checkpoint and resume from id's.

Pass nothing else.

This forces you to keep things serializable and therefore loggable, reproducible, parallelizable.

by the way try not to name them 'id' if you can add extra detail like 'runId', 'taskId', 'subTask2Id'.
Read 5 tweets
swyx Profile picture
Jan 12
was fun to work on this @latentspacepod post w/ @benhylak

inspired by "pivot token" literature, one gpt->o1 mental model shift i've made is the role of self-evaluation and -correction as an ESSENTIAL part of planning/reasoning.

with o1, you move the LLM-as-judge *INTO THE PROMPT*, so you can let it handle the self eval and replanning. this is the incremental next "agentic" step, which openai consistently does well, to the frustration of more hyperbolic but snake oily alternatives.Image
@latentspacepod @benhylak full context latent.space/p/o1-skill-iss…

and here

x.com/benhylak/statu…
@latentspacepod @benhylak shamelessly ripped off lmao
Read 5 tweets
swyx Profile picture
Dec 14, 2024
this neurips is really going to be remembered as the "end of pretraining" neurips

notes from doctor @polynoamial's talk on scaling test time compute today

(thank you @oh_that_hat for organizing) Image
Image
Image
all gains to date have been from scaling data and pretrain compute and yet LLMs cant solve simple problems like tictactoe

however inference costs have scaled much less. Image
goes back to libratus/pluribus work

poker model scaling from 2012-2015 - scaled 5x each year, but still lost dramatically (9 big bets per hundred) to poker pros in 80k hands

recalls familiar insight about humans taking longer to think for harder problems.

added 20s of search - reduced distance from nash equilibrium results reduced by a factor of 7 - roughly the equivalent of scaling up model size by 100,000xImage
Image
Image
Image
Read 22 tweets
swyx Profile picture
Oct 1, 2024
Here’s my @OpenAIDevs day thread for those following along. everyone else gotchu with videos and stuff so i will just give personal notes and aha moments thru the day

first observation: @sama MIA

GPT5 still mentioned and on the table



Image
Image
Image
Image
after some nice screenshot of Cocounsel, time for @romainhuet’s legendary live demos. o1 one-shots an ios app and does the frotnend/backend to control a drone.

ai controlled drones, what could go wrong?


Image
Image
Image
@romainhuet Realtime API announced!

starting with speech to speech support
all 6 adv voice mode voices supported

demo next Image
Read 43 tweets
swyx Profile picture
Sep 30, 2024
just realized NotebookLM is @GoogleDeepMind's ChatGPT moment

- "low key research preview"/"experimental"
- not monetized
- GPUs/TPUs immediately on fire
- SOTA proprietary new model buried in there with upgrade that weren't previously announced
- new AI UX that cleverly embeds LLM usage natively within the product features

in this case NBLM nailed multimodal RAG and I/O in a way that @ChatGPTapp never did (or for that matter, @GeminiApp). The multiple rounds of preprocessing described by @stevenbjohnson also raise the quality of the audio conversation dramatically at the cost of extreme latency (took an efficient model that was advertised as capable of generating 30s of audio in 0.5s, and slapped on like 200s of LLM latency haha)Image
@GoogleDeepMind like, i put my podcast into it and it made a podcast of my podcast and... it was good.

do u guys know we spend 1-2 hrs writing up the show notes and now its a button press in NBLM

@GoogleDeepMind - just hired @OfficialLoganK

if i had a penny for every time this has happened i'd have two pennies
Read 5 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

Send Email!

:(