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
Nick Dobos Profile picture
@NickADobos
May 14 • 8 tweets • 2 min read • Read on X
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
First download the app here:
persistent.oaistatic.com/sidekick/publi…
Then use charles, proxyman or your favorite network proxy to do this:

1. login once to trigger api calls, then

2. right click and choose map local, then replace every false with true

try again, and you should be in

ab.chatgpt.com/v1/initialize
Coming SOON!?
Sorry openAi, I want to play with it :)

Coming NOW.
DELVE IN Image
Also of note, the codename for this project appears to be "Sidekick". In case you were wondering where the app is headed
Also the default hotkey for the bar conflicts with Arc browser mini arc hotkey

RIP
There can only be ONE
ngl Im kinda hitting UI bar overwhelm

cmd+space for raycast
option+space for chatGPT
now I'm trying cmd+y for mini arc since its near cmd+t for arc's new tab & command bar
cmd+K in tons of apps, notably cursor

• • •

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

Keep Current with Nick Dobos

Nick Dobos 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 @NickADobos

Nick Dobos Profile picture
Feb 8
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"Image
Image
Image
Image
Trying to get it to write code, and not give commentary is basically impossible

Image
Image
Image
Here's another good review. I agree with most of it

Definitely a different tone. Less mechanical, and more wordy. Might need to change prompting style

Though I'm very skeptical of using benchmarks to place Gemini in GPT-4 tier



Image
Image
Read 4 tweets
Nick Dobos Profile picture
Jan 23
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 workImage
Image
Image
More info on supported file types:
platform.openai.com/docs/assistant…
Expanding on this a little bit

I think "documents" end up all 3 of
1. Searchable vector db via "Searching Knowledge"
2. Inside the system prompt as part of the tool "instructions"
3. In the sandbox data mnt, available to code interpreter

Where as "files"
only #3
Read 8 tweets
Nick Dobos Profile picture
Jan 4
This is not a real person
This not real handwriting

World is NOT ready for this level of catfish
Check the text: U/ your Mom

Welcome to the shitstorm
Heres her passport
Image
Image
Read 4 tweets
Nick Dobos Profile picture
Nov 24, 2023
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-…
As I've been using chatGPT for coding and other tasks,

I've noticed a super weird phenomenon, where having a prebuilt plan, seems to reduce the starting friction dramatically

This seemed to resonate, so I decided to build it into a full experience
Read 11 tweets
Nick Dobos Profile picture
Nov 24, 2023
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-…
Addressing the elephant / giant tentacle monster in the room:
Why did I make this?

I've seen quite a few similar OpenAPI schema generator GPTs, but I kept running into problems

So I scratched my own itch, with a tentacle
Read 22 tweets
Nick Dobos Profile picture
Nov 22, 2023
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.
But 3 issues

A. ) they drop in & out of the context window. Unlike a persistent system prompt

B. ) relies on triggering a tool first, so you kinda need to know what’s in the external source first

C.) long documents get clipped into context
Read 6 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!

:(