chanatun | building @ 16

[chanatun | building @ 16 @chanatundev]

im still sticking with @OpenBot_ though

[chanatun | building @ 16 @chanatundev]

Grok Bot v1.0 is out of beta, and it seems to be moving toward collaborative bots (maybe enterprise):

for us unenterprised X-lings:
> more proactive and spots unfinished work, offers to take it
> fewer needless approval cards
> faster+more reliable browser, docs, and slides; better at interactive pages

mainly enterprise:
> you can now share your bots (multi-person threads)
> integrates w/ Slack + can now join Google Meet, Zoom, and Teams; can chat in the call and send a summary
> shared app logins

https://t.co/qFNSA7KSUe

[chanatun | building @ 16 @chanatundev]

@AniC_dev boat patrols the moat surrounding the Tuileries

[chanatun | building @ 16 @chanatundev]

@lucastohdev @matthewmillerai @bridgemindai Bridgmind was assassinated by @theo

[chanatun | building @ 16 @chanatundev]

@norbertbodziony @theo openbot founder using t3code
theres no better combo 🫡🫡

[chanatun | building @ 16 @chanatundev]

@AniC_dev very educational. i also will not steal a car and i acknowledge that piracy is a crime

[chanatun | building @ 16 @chanatundev]

@maria_rcks @astuyve did he offer you 100% of t3 code's revenue?

[chanatun | building @ 16 @chanatundev]

@alexandr_wang I <3 pareto frontier and cheap models, thanks meta

[chanatun | building @ 16 @chanatundev]

misinformation.
its like comparing apple's dictation to wisprflow/willow voice.

@AarushYadav47 literally talks about this in his post: https://t.co/SlVrS4zyjE

"IMUs are very limited. We tried IMUs on glasses, masks, and earbuds. However, IMUs measure your aggregated facial movement.

It’s like being asked to develop Face ID but you’re only allowed a 1px by 1px image.

It works for a few discrete classes like classifying between 5 words,

because your head moves differently during yes and no, but carry that over to classifying 10K words or even on a phoneme basis, and it breaks down.

The precision issue is fatal. We quickly realized it's not the path to continuous speech decoding.

[bishara @bishara]

startup killed before it actually started

[chanatun | building @ 16 @chanatundev]

@watashikuraswa @shlummi they just explained in their previous post that earbuds measure aggregated movement and are basically only effective when classifying between small amounts of words:

https://t.co/lML9X8fjUx

[Aarush Yadav @AarushYadav47]

How we built the future of human-computer interaction https://t.co/Erk0Axx3nj

[chanatun | building @ 16 @chanatundev]

@shlummi this is a prototype

[chanatun | building @ 16 @chanatundev]

@itsindishere we have https://t.co/T2EEWFAQAj. i love it and run it on a spare laptop-turned server. its opensource btw

[chanatun | building @ 16 @chanatundev]

@AniC_dev does that mean that you don't work full time but all the time / no time?

[chanatun | building @ 16 @chanatundev]

@L1NKN_exe @reasonmachines @grok @bot @OpenBot_ @reasonmachines is meant more for coding more, and @OpenBot_ is meant to replace grokbot.

they both allow you to bring your own sub (eg codex), which is good because you don't want to run grok all the time.

[chanatun | building @ 16 @chanatundev]

@ryan_morr you already have your answer: https://t.co/zuzmEpu3pR

[Ryan Morrissey @ryan_morr]

The boat man never leaves my feed and now he is just stuck at the top of my app ominously

[chanatun | building @ 16 @chanatundev]

@dewyashtwts the new chat screen and ui in general is super similar to @trySynara

[chanatun | building @ 16 @chanatundev]

@thsottiaux will you give plus users dots someday? its our turn to have some benefits

[chanatun | building @ 16 @chanatundev]

@theo we need t3os w/ this please

[chanatun | building @ 16 @chanatundev]

@be_arsh please keep it minimal. users should add features themselves