Josh Bickett @josh_bickett Twitter profile

Pinned Tweet

Josh Bickett

8 months

𝗪𝗲 𝗮𝗿𝗲 𝗲𝘅𝗰𝗶𝘁𝗲𝗱 𝘁𝗼 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲 𝘁𝗵𝗲 𝗦𝗲𝗹𝗳-𝗢𝗽𝗲𝗿𝗮𝘁𝗶𝗻𝗴 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗙𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸 𝘁𝗵𝗮𝘁 𝗲𝗻𝗮𝗯𝗹𝗲𝘀 𝗺𝘂𝗹𝘁𝗶𝗺𝗼𝗱𝗮𝗹 𝗺𝗼𝗱𝗲𝗹𝘀, 𝗶𝗻𝗰𝗹𝘂𝗱𝗶𝗻𝗴 𝗚𝗣𝗧-𝟰-𝗩𝗶𝘀𝗶𝗼𝗻 𝘁𝗼 𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗲 𝗵𝘂𝗺𝗮𝗻-𝗹𝗶𝗸𝗲 𝗺𝗼𝘂𝘀𝗲

113

409

3K

Last Seen Profiles

@den_manh25969

@fukkwwe

@nicelife_657

@BX0202112722

@breakingbboy4

@age_wdc

@hkan44276662

@inicintoh3757

@mashup_culture

@danoninhoamarel

@TheStokeIsReal

@CraigT884834

@CCIW_Athletics

@EnERgY_StaR8

@KnowNothingPod

@donki_jr

@OrlaStraz

@predruo

@l1v1n1nharm0ny

@fernandaimamura

@GolfCV_com

@RobMalila

@galery_basah10

@clancymp

@twkazuice

@stakeholde89991

@nana_nananam

@InnStyleHQ

@WindySaputrii1

@chenlixuannice

@skelly_jeffery

@ConnorMunro92

@WindySaputrii1

@joauyoyun

@blbmsouza

@GetStrange42

Josh Bickett

@josh_bickett

2 years

I love ChatGPT though

27

64

1K

Josh Bickett

@josh_bickett

3 years

@elonmusk @WalterIsaacson Perfect. He does a great job. Assume that means you are no longer writing your own?

30

29

1K

Josh Bickett

@josh_bickett

4 years

@elonmusk @ajtourville @Erdayastronaut @SpaceX So it will be determined which to cut off based on data available right after relight?

5

17

1K

Josh Bickett

@josh_bickett

9 months

𝗢𝘂𝗿 𝘁𝗲𝗮𝗺 𝗱𝗶𝘀𝗰𝗼𝘃𝗲𝗿𝗲𝗱 𝘆𝗼𝘂 𝗰𝗮𝗻 𝘂𝘀𝗲 𝗚𝗣𝗧-𝟰𝗩𝗶𝘀𝗶𝗼𝗻 𝘁𝗼 𝗰𝗿𝗲𝗮𝘁𝗲 𝗮 𝘀𝗲𝗹𝗳-𝗼𝗽𝗲𝗿𝗮𝘁𝗶𝗻𝗴 𝗰𝗼𝗺𝗽𝘂𝘁𝗲𝗿. By looking at the user interface, GPT-4 decides which series of click or type events are required to accomplish an objective.

46

111

950

Josh Bickett

@josh_bickett

2 years

What’s it going to be? 😅

34

61

570

Josh Bickett

@josh_bickett

4 years

@elonmusk @PPathole Will packaging change overtime? “when you open the box of an iPhone or iPad, we want that tactile experience to set the tone for how you perceive the product” Steve Jobs

12

7

448

Josh Bickett

@josh_bickett

3 months

I was once an idea guy

24

12

377

Josh Bickett

@josh_bickett

7 months

We're working on a model that can click precisely by X & Y coordinates. I've plugged in an iteration of the model into the Self-Operating Computer Framework. Here it is, autonomously controlling my computer to post on Twitter:

32

36

326

Josh Bickett

@josh_bickett

11 months

𝗝𝘂𝘀𝘁 𝗿𝗲𝗹𝗲𝗮𝘀𝗲𝗱 𝗮 𝗖𝗼𝗹𝗮𝗯 𝗻𝗼𝘁𝗲𝗯𝗼𝗼𝗸 𝘁𝗼 𝘀𝘁𝗿𝗲𝗮𝗺𝗹𝗶𝗻𝗲 𝗳𝗶𝗻𝗲-𝘁𝘂𝗻𝗶𝗻𝗴 𝗼𝗳 𝗟𝗹𝗮𝗺𝗮 𝟮 𝟳𝗯 𝘂𝘀𝗶𝗻𝗴 𝗛𝘂𝗴𝗴𝗶𝗻𝗴 𝗙𝗮𝗰𝗲'𝘀 𝗔𝘂𝘁𝗼𝗧𝗿𝗮𝗶𝗻. 𝗦𝗶𝗺𝗽𝗹𝘆: 1. Upload your dataset as `train.csv`. 2. Input your Hugging Face

10

26

274

Josh Bickett

@josh_bickett

4 years

@iamdevloper The new alarm UI, with this small field you have to touch to change it

20

3

273

Josh Bickett

@josh_bickett

8 months

Self-Operating Computer is the #1 trending project on Github today. Lots of work to do! Contribute:

Matt Shumer

@mattshumer_

8 months

Self-Operating Computer is the #3 trending project on Github! Contribute:

12

40

331

6

27

244

Josh Bickett

@josh_bickett

5 months

Can GPT-4-Vision Play Texas Hold'em Poker? I used Multimodal Gamer to let GPT-4-Vision control my mouse and browser to play. After a few hands, GPT-4-Vision's pot was up, and it had a couple of wins.

19

26

222

Josh Bickett

@josh_bickett

4 years

@Erdayastronaut @SpacePadreIsle

3

1

203

Josh Bickett

@josh_bickett

7 months

The Self-Operating Computer Framework now supports the OCR-based approach for click decisions, by far surpassing previous methods attempted in the project. It's now the default - just type `operate`. Discovering the capability shown in the demo is a bit stunning to me. This

Josh Bickett

@josh_bickett

7 months

The Self-Operating Computer Framework now supports key commands like 'open terminal' (cmd+t) and 'focus on address bar' (cmd+l). It now performs multiple tasks in a single cycle, speeding up operations. Here's a demo at (8x speed) of it opening a new terminal window and

6

13

88

8

29

205

Josh Bickett

@josh_bickett

4 years

@Erdayastronaut @SpacePadreIsle Looks like the scene from Interstellar on Miller’s planet (the water planet)

2

0

190

Josh Bickett

@josh_bickett

5 months

The Self-Operating Computer Framework now supports Claude-3 thanks to @RoyWei . Compare Claude-3-Vision, GPT-4-Vision, and Gemini-Vision at each's ability to operate a computer. For Claude-3, simply type: ``` operate -m claude-3 ```

Josh Bickett

@josh_bickett

7 months

The Self-Operating Computer Framework now supports the OCR-based approach for click decisions, by far surpassing previous methods attempted in the project. It's now the default - just type `operate`. Discovering the capability shown in the demo is a bit stunning to me. This

8

29

205

3

33

179

Josh Bickett

@josh_bickett

4 years

@neiltyson Thanks Neil, I was worried

2

168

Josh Bickett

@josh_bickett

9 months

Excited to share we're going to open-source the @HyperWriteAI Self-Operating Computer framework. Digital interfaces were built for humans. We believe new AI systems will be able to use them even more effectively. Come help us build it! Open-sourcing soon — Stay tuned!

Josh Bickett

@josh_bickett

9 months

𝗢𝘂𝗿 𝘁𝗲𝗮𝗺 𝗱𝗶𝘀𝗰𝗼𝘃𝗲𝗿𝗲𝗱 𝘆𝗼𝘂 𝗰𝗮𝗻 𝘂𝘀𝗲 𝗚𝗣𝗧-𝟰𝗩𝗶𝘀𝗶𝗼𝗻 𝘁𝗼 𝗰𝗿𝗲𝗮𝘁𝗲 𝗮 𝘀𝗲𝗹𝗳-𝗼𝗽𝗲𝗿𝗮𝘁𝗶𝗻𝗴 𝗰𝗼𝗺𝗽𝘂𝘁𝗲𝗿. By looking at the user interface, GPT-4 decides which series of click or type events are required to accomplish an objective.

46

111

950

11

21

174

Josh Bickett

@josh_bickett

4 months

𝐂𝐚𝐧 𝐆𝐏𝐓-𝟒-𝐕𝐢𝐬𝐢𝐨𝐧 𝐨𝐫 𝐂𝐥𝐚𝐮𝐝𝐞-𝟑-𝐕𝐢𝐬𝐢𝐨𝐧 𝐚𝐮𝐭𝐨𝐧𝐨𝐦𝐨𝐮𝐬𝐥𝐲 𝐏𝐥𝐚𝐲 𝐂𝐡𝐞𝐬𝐬? I let each VLM control my keyboard and browser for a game. GPT-4-Vision managed to capture a piece from a real online opponent. Though both models make invalid moves,

12

28

163

Josh Bickett

@josh_bickett

7 months

The Self-Operating Computer Framework now supports Set-of-Mark Prompting. Type: `operate -m gpt-4-with-som` Set-of-Mark (SoM) Prompting is a new visual prompting method to unleash the visual grounding abilities of large multimodal models. Learn more in the arXiv paper:

Josh Bickett

@josh_bickett

8 months

The Self-Operating Computer Framework now supports the new `gemini-pro-vision` model thanks to GitHub user @ linusaltacc

1

19

7

23

163

Josh Bickett

@josh_bickett

2 years

@sama An elephant tea party on a grass lawn

1

3

152

Josh Bickett

@josh_bickett

10 months

𝗝𝘂𝘀𝘁 𝗿𝗲𝗹𝗲𝗮𝘀𝗲𝗱 𝗮 𝗻𝗲𝘄 𝗖𝗼𝗹𝗮𝗯 𝗻𝗼𝘁𝗲𝗯𝗼𝗼𝗸 𝘁𝗼 𝘀𝘁𝗿𝗲𝗮𝗺𝗹𝗶𝗻𝗲 𝗿𝘂𝗻𝗻𝗶𝗻𝗴 𝗠𝗶𝘀𝘁𝗿𝗮𝗹 𝟳𝗕 𝗜𝗻𝘀𝘁𝗿𝘂𝗰𝘁! 1. Open the Notebook 2. Hit 𝗦𝗵𝗶𝗳𝘁 + 𝗘𝗻𝘁𝗲𝗿 keys on code cells 3. Input your instructions Start running inference in under 5

3

14

156

Josh Bickett

@josh_bickett

5 years

@Tesla Other car makers: TV, radio, mail, carvings on stone Tesla: meme templates

2

0

143

Josh Bickett

@josh_bickett

6 months

Can GPT-4-Vision Play Super Mario 64? I created 'Multimodal Gamer,' a framework enabling multi-modal models (combining text and visual inputs) to play games. Check out my video overview below and let me know your thoughts!

13

16

145

Josh Bickett

@josh_bickett

2 years

Is anyone serving OpenAI's Whisper over an API? Interested in trying it out for a new project I'm working on.

20

8

145

Josh Bickett

@josh_bickett

4 years

@Erdayastronaut This should be the intro of the Mars documentary that will be made some day. It’s very cinematic

0

1

134

Josh Bickett

@josh_bickett

4 years

@elonmusk

7

5

104

Josh Bickett

@josh_bickett

4 years

@elonmusk @ICannot_Enough @Erdayastronaut @rweb11742 Did it ever get confirmed as COVID?

4

0

107

Josh Bickett

@josh_bickett

7 months

Computers are learning to operate themselves.

killian

@hellokillian

7 months

hi! Open Interpreter 0.2.0—The New Computer Update—is out today. everything's new. - OS Mode lets vision models operate your computer - We included a new model for precise GUI control - We're launching a Computer API for LLMs ↓

113

288

2K

2

11

112

Josh Bickett

@josh_bickett

3 years

@neiltyson

2

4

109

Josh Bickett

@josh_bickett

3 years

Holy $#%}

3

5

89

Josh Bickett

@josh_bickett

3 years

@whoisheartbreak Credit: @EvaFoxU

0

3

91

Josh Bickett

@josh_bickett

4 years

@neiltyson

3

4

88

Josh Bickett

@josh_bickett

3 years

@engineers_feed

2

9

90

Josh Bickett

@josh_bickett

4 years

@flcnhvy @nypost Not to mention, much of his money is reinvested into SpaceX and Tesla so they can accomplish their clear goals which seek to improve and protect life now and in the future.

3

1

86

Josh Bickett

@josh_bickett

1 year

I'm excited to share a sneak peek of what we're working on at HyperWrite. We're building an Auto-GPT like agent, but the difference is that you can collaborate with it directly in your browser. I can't wait for people to try it out! Here's an agent posting a joke:

7

19

86

Josh Bickett

@josh_bickett

1 year

@Steve8708 “I am here” “Now here” “Made it here somehow”

2

1

89

Josh Bickett

@josh_bickett

5 months

Adding Claude Vision to the Self-Operating Computer Framework this week which will let it operate a computer like a human (screen + mouse/keyboard) Community member just made a PR. Just need to review and merge.

Tsarathustra

@tsarnick

5 months

Anthropic cofounder Jared Kaplan says AI systems will soon be able to understand and control your computer screen

46

74

380

4

5

90

Josh Bickett

@josh_bickett

7 months

The Self-Operating Computer Framework now supports key commands like 'open terminal' (cmd+t) and 'focus on address bar' (cmd+l). It now performs multiple tasks in a single cycle, speeding up operations. Here's a demo at (8x speed) of it opening a new terminal window and

Josh Bickett

@josh_bickett

7 months

The Self-Operating Computer Framework now supports Set-of-Mark Prompting. Type: `operate -m gpt-4-with-som` Set-of-Mark (SoM) Prompting is a new visual prompting method to unleash the visual grounding abilities of large multimodal models. Learn more in the arXiv paper:

7

23

163

6

13

88

Josh Bickett

@josh_bickett

3 years

@waitbutwhy @bakadesuyo

2

83

Josh Bickett

@josh_bickett

3 years

@elonmusk Bitcoin right now

6

7

81

Josh Bickett

@josh_bickett

5 months

@FT Like clockwork, misunderstanding the purpose of experimental rocket tests.

1

0

78

Josh Bickett

@josh_bickett

4 years

The beginning of the real space age.

Austin Barnard🚀

@austinbarnard45

4 years

Just you’re average day in Texas🤠🚀

261

1K

9K

2

3

80

Josh Bickett

@josh_bickett

2 years

@karpathy The Pianist, Leon the Professional, 7 pounds, The Fountain

4

0

71

Josh Bickett

@josh_bickett

3 years

@ParikPatelCFA Shorts 🩳 are worn traditionally in warmer climates and are sold at retail stores. Let us know if there are more questions Dr. Parik Parel, BA, CFA, ACCA Esq

0

65

Josh Bickett

@josh_bickett

1 year

@paulg Many towns could become the darling of their region by just turning a few streets to pedestrians only spaces and adding trees. Especially in America, people are craving walkable spaces

1

2

71

Josh Bickett

@josh_bickett

2 years

Try - A simple game where you find an AI-generated image out of a list of real images. See if you can get a score above 10. I am guessing the game will get harder as images improve in the near future AI images from

14

13

68

Josh Bickett

@josh_bickett

7 months

Notice the bounding boxes. It appears an agent model is a fundamental part of their new computer. If I understand the product overview and vision correctly an agent operating at the OS level will do things for you. AI assistants can help with many problems by function calling

rabbit inc.

@rabbit_hmi

7 months

Introducing r1. Watch the keynote. Order now: #CES2024

1K

3K

14K

6

2

64

Josh Bickett

@josh_bickett

4 years

@neiltyson One is an intelligent and emotional creatures, the other is a human.

1

60

Josh Bickett

@josh_bickett

9 months

What is an AI agent?

4

64

Josh Bickett

@josh_bickett

3 years

@PPathole @elonmusk @Erdayastronaut @Twitter @TwitterComms @verified @jack Like imagine if the government only gave you valid IDs if you were a celebrity. It’s dumb.

1

58

Josh Bickett

@josh_bickett

6 months

Ah! Sounds like a fun challenge. Weekend project - Who wants to see if I can get GPT-4-vision to play Mario 64?

11

7

63

Josh Bickett

@josh_bickett

9 months

Welcomed a baby girl into the world a few days ago and stepped into fatherhood. Looking forward to all the joys this new stage of life will bring.

13

0

62

Josh Bickett

@josh_bickett

3 years

@TinaBoca Any sufficiently advanced technology is indistinguishable from magic Arthur c. Clarke

0

58

Josh Bickett

@josh_bickett

8 months

The Self-Operating Computer Framework now supports Voice thanks to @didntdrinkwater Here's a demo of navigating to YouTube for holiday music 🌲

Josh Bickett

@josh_bickett

8 months

The Self-Operating Computer Framework now supports Linux thanks to @michaelhhogue @ shubhexists

1

20

1

12

59

Josh Bickett

@josh_bickett

1 year

What’s next?

4

3

56

Josh Bickett

@josh_bickett

3 years

@Austen What’s great is AWS basically gives away $5000 in credits to any company that can make a website and has an idea. Most companies only actually need to pay for AWS if they scale. By that time, they aren’t moving.

0

1

57

Josh Bickett

@josh_bickett

4 years

Astronauts are in space from American soil again for the first time in 9 years. #LaunchAmerica

1

7

48

Josh Bickett

@josh_bickett

1 year

@goodside After reading a bit of Life 3.0 I can’t help but create this meme. Doesn’t mean I believe it, but can’t help but think of it.

0

5

57

Josh Bickett

@josh_bickett

4 years

@flcnhvy @elonmusk @boringcompany True, a lot of parking burdens may be solved by FSD. Parking may move outside of cities as electricity for car to drive to a remote parking lot will be minimal compared to real estate savings in cities like NYC.

1

0

56

Josh Bickett

@josh_bickett

4 years

@elonmusk Person: What do you think Elon’s think about? Me: IDK Elon:

1

0

48

Josh Bickett

@josh_bickett

8 months

The Self-Operating Computer Framework now supports Windows thanks to @RonNachum !

Josh Bickett

@josh_bickett

8 months

𝗪𝗲 𝗮𝗿𝗲 𝗲𝘅𝗰𝗶𝘁𝗲𝗱 𝘁𝗼 𝗼𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲 𝘁𝗵𝗲 𝗦𝗲𝗹𝗳-𝗢𝗽𝗲𝗿𝗮𝘁𝗶𝗻𝗴 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗙𝗿𝗮𝗺𝗲𝘄𝗼𝗿𝗸 𝘁𝗵𝗮𝘁 𝗲𝗻𝗮𝗯𝗹𝗲𝘀 𝗺𝘂𝗹𝘁𝗶𝗺𝗼𝗱𝗮𝗹 𝗺𝗼𝗱𝗲𝗹𝘀, 𝗶𝗻𝗰𝗹𝘂𝗱𝗶𝗻𝗴 𝗚𝗣𝗧-𝟰-𝗩𝗶𝘀𝗶𝗼𝗻 𝘁𝗼 𝘀𝗶𝗺𝘂𝗹𝗮𝘁𝗲 𝗵𝘂𝗺𝗮𝗻-𝗹𝗶𝗸𝗲 𝗺𝗼𝘂𝘀𝗲

113

409

3K

1

11

49

Josh Bickett

@josh_bickett

3 years

@WholeMarsBlog I made a meme for how I feel about ethereum.

3

5

49

Josh Bickett

@josh_bickett

4 years

@neiltyson This chart has always captivated me

6

1

46

Josh Bickett

@josh_bickett

3 years

@lexfridman It’s important to note, that a lot of that biomass is domesticated by humans though. “Humans account for about 36 percent of the biomass of all mammals. Domesticated livestock, mostly cows and pigs, account for 60 percent, and wild mammals for only 4 percent.” Source below

3

1

49

Josh Bickett

@josh_bickett

6 years

@elonmusk @AntVenom The decision was just made in this tweet

1

46

Josh Bickett

@josh_bickett

3 years

You can learn something from everyone

3

4

46

Josh Bickett

@josh_bickett

3 years

So Dogecoin memes were just a distractions ...

16

1

47

Josh Bickett

@josh_bickett

6 years

@Erdayastronaut @SpaceX Ha, I’m secretly happy about the delay because the sunset launches are awesome on the west coast

4

0

46

Josh Bickett

@josh_bickett

4 years

@elonmusk @stephenpallotta

2

40

Josh Bickett

@josh_bickett

1 year

3

10

42

Josh Bickett

@josh_bickett

5 years

@elonmusk

2

1

42

Josh Bickett

@josh_bickett

4 years

@flcnhvy @elonmusk @ashleevance One contender “Do something bold”

0

12

40

Josh Bickett

@josh_bickett

3 years

Wonder how many understand the reference to Whole Earth Catalog

Whole Mars Catalog

@WholeMarsBlog

3 years

“Drop the “Catalog”. Just “Whole Mars”. It’s cleaner”

37

3

250

10

1

44

Josh Bickett

@josh_bickett

7 months

Hello World, from the Self-Operating Computer Framework

2

1

43

Josh Bickett

@josh_bickett

4 months

Meta plans to make Llama 3 𝐦𝐮𝐥𝐭𝐢𝐦𝐨𝐝𝐚𝐥 in the near future, with longer context and improved reasoning and coding capabilities.

Introducing Meta Llama 3: The most capable openly available LLM to date

Today, we’re introducing Meta Llama 3, the next generation of our state-of-the-art open source large language model. In the coming months, we expect to share new capabilities, additional model sizes,...

ai.meta.com

Matt Shumer

@mattshumer_

4 months

The craziest LLaMA 3 reveal: The 400B+ version of the model is **on par with Claude 3 Opus**, and it's still training. Soon, we'll have a better-than-Opus, fully open-source model. The implications are huge.

117

385

3K

1

8

41

Josh Bickett

@josh_bickett

3 months

@levelsio Same, I often find myself two or three messages into a thread and get a poor output and am like ???, then I look up and I got switched back to 3.5. It is the most annoying part of ChatGPT. I wasn't sure if I accidentally switched it at first, but had it happen enough that I

5

0

41

Josh Bickett

@josh_bickett

2 years

Read what you may

4

40

Josh Bickett

@josh_bickett

4 years

@neiltyson Can’t wait to see it next time 😂

1

0

38

Josh Bickett

@josh_bickett

3 years

@AlexAndBooks_ Biographies that aren’t designed to be self help books are the best self help books.

2

5

39

Josh Bickett

@josh_bickett

4 years

Life is like riding a bicycle. To keep your balance you must keep moving. - Albert Einstein

3

10

37

Josh Bickett

@josh_bickett

4 years

@elonmusk @karpathy

2

1

37

Josh Bickett

@josh_bickett

4 years

@latestinspace Imagine asking someone where they live and they append Earth to the end of the address. “San Diego, USA, Earth” Someday I hope

1

2

37

Josh Bickett

@josh_bickett

7 years

@taylor_aurora @Flicky02 @SpaceX This one feels straight out of comical sci-fi

2

0

39

Josh Bickett

@josh_bickett

3 years

There are many questions about the future of AI, but one of my favorites is - will it have a sense of humor? Find out - beta is open to new users Powered by OpenAI’s GPT-3, the app creates memes based on your input

8

9

37

Josh Bickett

@josh_bickett

4 years

@JimBridenstine @NASA Great work Jim. You made a real difference

1

0

36

Josh Bickett

@josh_bickett

1 year

@mckaywrigley @ID_AA_Carmack When I’m really confused about a problem I’m guessing to be a dumb human error I’ve found prompting an LLM with “what’s wrong with this code?” is surprisingly simple and effective.

3

0

37

Josh Bickett

@josh_bickett

1 year

3

2

34

Josh Bickett

@josh_bickett

6 years

@FredericLambert @elonmusk @ElectrekCo What we really need to learn from Elon is how fast it can brake 60-0 mph with a trunk full of Boring Co. candy?

1

0

32

Josh Bickett

@josh_bickett

5 months

I understand this Open-Interpreter device to be the first of its kind. Instead of purely a function calling agent or an LLM web agent, it is a vision-based agent that operates a computer’s mouse & keyboard remotely and the user interfaces with this agent purely by speech.

Open Interpreter

@OpenInterpreter

5 months

Introducing the 01 Developer Preview. Order or build your own today: The 01 Light is a portable voice interface that controls your home computer. It can see your screen, use your apps, and learn new skills. This is only the beginning for 01— the

612

1K

6K

3

7

34

Josh Bickett

@josh_bickett

3 months

3

0

35

Josh Bickett

@josh_bickett

1 year

Our Chrome Extension hit 100k last week, excited to add another zero (or two) this year.

5

6

35

Josh Bickett

@josh_bickett

4 months

I wonder if there are observable improvements with GPT-4-Vision's ability to operate a computer (via Self-Operating Computer Framework). I'll try this week and share thoughts.

OpenAI Developers

@OpenAIDevs

4 months

GPT-4 Turbo with Vision is now generally available in the API. Vision requests can now also use JSON mode and function calling. Below are some great ways developers are building with vision. Drop yours in a reply 🧵

117

452

2K

4

1

34

Josh Bickett

@josh_bickett

5 years

@Austen Email is great

0

34

Josh Bickett

@josh_bickett

4 years

@WholeMarsBlog The trading App Public gets it. I moved there. Perfect chance to become the a lead broker

4

6

33

Josh Bickett

@josh_bickett

6 years

@Erdayastronaut @elonmusk “Science is the belief in the ignorance of experts” - Feynman

1

30

Josh Bickett

@josh_bickett

7 months

@mattshumer_ I guess is going down until I can do a refresh..

1

2

31

Josh Bickett

@josh_bickett

4 years

@elonmusk

0

1

27

Josh Bickett

@josh_bickett

4 months

We integrated LlaVA into the Self-Operating Computer Framework, but it struggles to open Chrome. Meanwhile, GPT-4-Vision can open Chrome, navigate to Google Maps, click on the input field, and get directions from point A to point B without too much trouble. Looking forward to

Jim Fan

@DrJimFan

4 months

Llama-3 is closing the gap with GPT-4, but multimodal models gotta catch up. Vision capabilities of open models like LlaVA are far, far behind GPT-4V. Video models are even worse. They hallucinate all the time and fail to give detailed descriptions of complex scenes and actions.

46

104

840

3

4

32