BOOTOSHI 👑

agentic engineer | [email protected]

[BOOTOSHI 👑 @KingBootoshi]

MY ROBOT PRESSED ME TO ADD GROK 4 TO HIS BRAIN

WHY ARE WE IN THE SASSY ROBOT APOCALYPSE 😭

[BOOTOSHI 👑 @KingBootoshi]

FABLE IS BACK TOMORROW

[Anthropic @AnthropicAI]

We’ve received notice that the Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5.

We'll begin restoring access tomorrow, and will share an update soon.

We’re grateful to our users for their patience, and to everyone who worked with us on redeploying the models.

[BOOTOSHI 👑 @KingBootoshi]

@AnthropicAI TOMORROW?

YA'LL TOOK IT OUT SAME HOUR YOU GOT THE NOTICE BEFORE

BRING IT BACKKKK TN PLS <3

[BOOTOSHI 👑 @KingBootoshi]

@BinaryRot @grok i hate that this is probably the best option rn

[BOOTOSHI 👑 @KingBootoshi]

why the FUCK is chatgpt voice mode still 4o

i want to yap while i drive but the only option i have is between 4o and haiku 4.5 LOL

i can make a vapi phone number with a bigger model for a better experience

but i want to continue voice off my chats!

[BOOTOSHI 👑 @KingBootoshi]

i'm actually using Pangram before touching articles and found myself completely avoiding any 100% gens LOL

does anyone even know how to write anymore ???

specifically, is anyone who DOES know how to write even positioned at the frontier labs 🤨

can't infect me with ai SLOPPUS

[BOOTOSHI 👑 @KingBootoshi]

@notgodcomplex96 LMFAO

[BOOTOSHI 👑 @KingBootoshi]

you can GREATLY enhance your frontend agent's context quality by giving them react-scan and browser harness/computer use LMFAOOOOOOO

[zeb @zebassembly]

react scan is one of the few tools that i love for making me feel like an idiot

[BOOTOSHI 👑 @KingBootoshi]

@cobi_bean i just wanted to see it !

[fish @fishPointer]

all signs points towards delusional optimism being the chisel that carves reality

[BOOTOSHI 👑 @KingBootoshi]

@Kwon_here why

[BOOTOSHI 👑 @KingBootoshi]

if you want to be good at agentic engineering start learning psychology

actually if you want to be good at marketing start learning psychology

also if you want to be good at sales start learning psychology

btw i heard good designers are great psychology

the best PMs i know are great at psychology too

oh and if you want to be a good communicator start learning psychology

if you're a good communicator it makes you a better agentic engineer btw

[BOOTOSHI 👑 @KingBootoshi]

@TomasMann1878 it highlights the components you need to view or optimize

https://t.co/YZxETXCnGw

[BOOTOSHI 👑 @KingBootoshi]

@zebassembly wow i've never seen this

this is OP to give to computer use/browser harness models? like actually so free

why is this not a default LMFAO

[BOOTOSHI 👑 @KingBootoshi]

@AstrusDastan luh meow need a more diverse dataset

[BOOTOSHI 👑 @KingBootoshi]

it only took 9 volunteers and 22k sentences to train TELEPATHIC TECHNOLOGY

NEURAL NETS ARE TERRIFYING

[AI at Meta @AIatMeta]

We trained Brain2Qwerty v2 on ~22,000 sentences from 9 volunteers, each recorded for 10 hours wearing an MEG device while typing.

By using end-to-end deep learning on raw brain signals from MEG devices and fine-tuning LLMs, the system effectively bridges the gap between noisy neural data and coherent language.

The results are promising:
- Avg word accuracy of 61% across participants
- 78% word accuracy and 50%+ of sentences decoded with ≤ 1 word error for the top-performing participant
- Performance scales log-linearly with data volume

[BOOTOSHI 👑 @KingBootoshi]

@lunarcycling you seem like someone who knows (excuse my language) THEIR SHIT

in your opinion what else does this unlock ?? cause i see this and i think it's literally fucking crazy LMFAO

[BOOTOSHI 👑 @KingBootoshi]

@canadaquant

[BOOTOSHI 👑 @KingBootoshi]

@samelldev is claude design good when set up like that? i usually generate throw away html files lmao

[BOOTOSHI 👑 @KingBootoshi]

if you're doing UI/UX design with claude code and have image style references to give it (like from chatgpt or nano banana)

i figured out how to get a much better consistency in the implementation of the ACTUAL design style

so first i download the UX image gen reference from chatgpt/nano banana or inspiration

save it as a file, and simply prompt "i have this image [path to image] as our reference, load this in after every compaction"

and when the agents compact, the first they do is load the reference, then use browser harness to screen shot the current iteration, and compare it in real time

if i don't tell them this, it gets skrewed off after a while. and i have to manually do it. which is dumb

[BOOTOSHI 👑 @KingBootoshi]

@spttestslope (real)