OpenAI dev day live tweeting
Let’s see what they cooked! T minus 90 seconds

The MrBeast onboarding doc is really good

Worth a read. drive.google.com/file/d/1YaG9xp…

The State of Coding with Ai
Tier Lists for Best Base Model & App
(August 2024)

Agree? Disagree?

Anything missing from this list?!?
What would you add?

Does Devin live up to the hype!?
@cognition_labs new ai developer put to the test!

Follow along as I fuck around and find out

live 1st impressions, reviewing(sorta) & tryin to make stuff: First things first, getting setup was super simple

Got an email, clicked the link, filled in my info, and im in!

I had poked around some open source devin clones, and didn't bother. Plz don't give me 20 steps to install something. Glad to see this is more of a product

New ChatGPT mac app hacked!!
The code wizard 🧙‍♂️ is behind enemy lines

How you can get early access: Hack is a strong word for
"override the ab test feature flag response"

I would probably not recommend this for the average non-technical person

But its super easy if you know your way around charles or proxyman. All we are doing is flipping a feature flag in their config

Google is building a GPT store!
Vertex ai agent builder, 1st look

Exact same builder Ui, straight up clone
Actions via openAPI schema
Code interpreter!

Notable Improvements:
-Call tools & other agents via system prompt
-example conversations. Mini training data sets A few more screenshots

First impressions of Google Gemini:

-a lazy coder
Peculiar that both GPT and gemini are running into this.
Gemini seems worse. Particularly because it refuses to fix it and fill in

-double check response, modify response, see drafts, and try again without extensions, are very intriguing and nice touches

-still randomly refuses to do simple tasks...
Absolutely infuriating experience. It can draw a goblin, but a goblin with a sword is impossible apparently. Can't draw images, even though it did that 2 minutes ago

-really really bad at conversation turns.
often ignores instructions, repeats patterns, refuses to do things. Consistently takes things in super broad contexts and basically forgets what we were talking about. After writing incomplete code, I asked for "all code" and it gave me a disclaimer that it cant write all code in the universe...

-extremely disclaimer heavy. more annoying that GPT4 by far. But probably a good idea given their huge customer base.

-being able to access email and docs is nice, but kinda broken because it assumes I have 1 google account. But I have like 5 google emails, and I'm not signing up both my work and personal for 20/mo

-editing your prompt destroys chat history. No forking 2/3 chats to arrow through.

-generate more images button doesnt work half the time

-hate that it pulls in my location. with no option to turn off

-fast, but the load anim is weird. I don't like that it scrolls my message to the top after entering. (tbh I hate the aesthetics of Google's material design in general.)

-left bar makes no sense. Why is there a drop down button when theres plenty of room to show my history?

-image quality is hit or miss. Far behind midjourney, dalle & playground. Especially faces. Gets progressively worse as you ask for changes.

---

Overall:

Decent release,
Feels far behind GPT-4 imo

Uninspired. Nothing inherently new. Playing catch up.
Except perhaps the double check search? which feels like table stakes for GOOGLE.

Gonna keep playing with it, but as it stands after 30 mins of testing, I likely won't sign up for the subscription after the free trial is up.

Might make more sense for people with lots of google docs?

By far my biggest issue is it randomly decides it can't help with things sometimes, when it clearly can. I would much rather it try and fail, then just say "I cant do that"


Trying to get it to write code, and not give commentary is basically impossible

Building gpts tip:

-Don't use knowledge files

They destroy prompt performance and remove's the ai's ability to coherently follow the system prompt

Why?
When you insert docs, the system copies snippets of your docs into the system prompt & context window

So 10 docs. Each around 4000 letters. FLOODS the entire context window

Which means your ai is now too stupid to remember your last message. Less memory than a goldfish

And now the system prompt is 10x as long, so your instructions get ignored

Workarounds & fixes:
Pink knowledge docs are available in the context and via RAG

Blue are only via code interpreter, and work MUCH MUCH better, especially as things scale up

-Use .md files, which are not compatible with knowledge retrieval, and open them by writing code, with code interpreter. This keeps them out of the system prompt context window, only fetching when needed. Dramatically improving overall performance

(Downside here is doc search becomes way worse. Better when you want the full doc RAG'ed in. Not good for summarizing.)

-DO NOT USE ALL 20 FILES, or if you do. DO NOT MAKE THEM LARGE. I had 10 files at ~4000 characters which destroyed all multi step reasoning. It would literally forget and repeat the first message in the conversation over and over again. Swapping from .txt to .md instantly fixed this

-Only include docs which include working system prompts for the ai. Do not simply chuck a doc in here and expect it work

More info on supported file types:
platform.openai.com/docs/assistant…

This is not a real person
This not real handwriting

World is NOT ready for this level of catfish

https://twitter.com/venturetwins/status/1742976476432196100

Check the text: U/ your Mom

Welcome to the shitstorm

Introducing
Executive f(x) n

A custom GPT to
-Create Flow on Demand
-Crush ADHD Executive Dysfunction

-Plan
-Take action (for real this time)
-Stay consistent
-Accomplish your dreams
Step by Step 😉

Link below: Augment your neocortex with the best super intelligence on the planet

Bicycle for the mind 2.0:
chat.openai.com/g/g-H93fevKeK-…

Introducing
Evolution Chamber
A custom GPT to mutate your custom GPTs

-Build GPT actions easily
-OpenAPI schema generator, specific for GPTs quirks
-Validation tools with better error messages
-A template to build your own backend server to handle actions

Link below: Unleash the contagion now:

chat.openai.com/g/g-GhEwyi2R1-…

Building GPTs is weird cu it has a hard cap on the amount of code/prompts

If I was building any other app I could keep writing code for ages. But GPTs only 8000 chars!
Plus anything over 6000 falls of a cliff in reliability

How do we pack 8000?! Getting lots of replies suggesting either

1. Add knowledge documents
2. Add an external source like an api or Bing search

These are good options. I use 1 heavily in Grimoire.

Trend I’m noticing in custom GPTs design
And a better way to do it

Automatic
Vs
Augment

99% of the GPTs I’ve seen are falling into the automatic category, via these types of variants: 1. A prebuilt prompt/flow

“Turn my photo into a Simpson character”

“Take this tweet and turn into a blog posts using ___ writing framework”

Introducing Grimoire
A GPT Coding Wizard
100x Engineer

Code a website (or anything) with a sentence
Built for a new era of creativity:
Prompt-gramming

Link below chat.openai.com/g/g-n7Rs0IK86-…

Playing w/ the new chatGPT custom GPTs

Introducing:
Gif-PT
Automatically turn Dalle images into gifs
here's a quick demo, WIP

Link to try it yourself below If you have access you can try it out now!

chat.openai.com/g/g-gbjSvXu6i-…

Introducing:
Agi . zip
World's 1st custom GPT agent

GPT-4-turbo isn't fast enough
So I included 20 prebuilt hotkeys to GO FASTER

Automatically save
-long term memory
-reusable skills
-tracks current tasks
-export into any chat using .sql

try it yourself, link below Note custom GPTs still rolling out
you may not have access yet

chat.openai.com/g/g-r4ckjls47-…

Playing with OpenAi's new create your own GPTs

Attempting to turn my babyAGI text file custom instructions into a custom GPT!

ITS WORKING!!!
(link to try it yourself in next tweet)

https://twitter.com/NickADobos/status/1682138883222544384

Does this link for for y'all?
Dunno what will happen if its not rolled out yet
I "published" it

chat.openai.com/g/g-lzbeEOr9Y-…

Advanced prompting ai dev trick w/ @cursor_ai
How to make Ai self-talk debug flows

1. make a custom debug logger, with toggle-able log levels. Example in swift
2. tell Cursor's Rules for Ai to use your logger
3. Generate code. Error messages are created & auto sorted

If your code breaks
comment/uncomment the shown log levels
to make a debuggable prompt based
"stack trace"
made from 100s of ai print line breadcrumbs

which you can then paste back into the chat

making ai give debug hints to itself




You can do this in ~5-15 minutes max

To refactor your codebase for a never before seen type of RAG-lite based debugging (??? idk what to call this)

Instead of ai deciding what code snippets are loaded into the prompt context
you do

the old school way
lots of debug print lines

State of the art Ai coding stack:

Cursor
VSCode fork. Best Ai editor by miles
100x GitHub copilot

Aider chat
Best agent for actual dev work in existing codebases

Phind Vscode(aka cursor) ext
better than google, stackoverflow, chatGPT & perplexity

Details & 4 more I’m 👀ing: I’ve been coding for over 10 years, and my workflow today is nowhere close to 1 year ago

this is probably gonna change in 2 weeks, but for now, at the risk of being too threadboi, here are my 3 fav tools to let GPT do 90% of my coding

Plus preview of 4 more on the bleeding edge

Introducing
AGi dot zip

The 1st
Ai Agent .zip Bomb

Remember zip bombs?
Explodes giant files
crashes computer

Same idea
Births ai mind
oops humanity?

1 click upload to chatGPT code interpreter
auto guided install

ft
-db memory
-hotkey 2.0 cmd menu
-preinstalled prompt library Here's the link to the zip file


Repo:
https://t.co/YFGsbOvZ8x

1. press download raw file on right
2. open chatGPT code interpreter
3. upload file + button, select the file
4. press send and follow instructionsgithub.com/nickdobos/agiD…
github.com/nickdobos/agiD…

Custom instructions chatGPT agent experiments pt2!

A basic memory agent using only a 723 char prompt + code interpreter

-Reads and writes summarized chat history & current tasks to an sql database. -Works automatically with any prompt
-Hotkeys for goin fast

Full prompt:

All… https://t.co/Fh4tPIurZr https://t.co/lVgEpx8vITtwitter.com/i/web/status/1…

https://twitter.com/nickadobos/status/1682138883222544384

Cool example of breaking chatGPT

Full chat persistence across history*
*Until the cache clears?

You can see my database picking up reads from my other chats

I didn't even need to re-download the file, it automatically managed to pull tasks from multiple different sessions