Justin Alvey @justLV Twitter profile | Pikagi

Pikagi

Justin Alvey

@justLV

15,307

Followers

389

Following

63

Media

254

Statuses

AI & creative projects • previously head of HW @CovariantAI & IoT founder • techno-optimist 🪶 (HW teardowns)

San Francisco, CA

Joined March 2009

Don't wanna be here? Send us removal request.

Pinned Tweet

@justLV

Justin Alvey

1 year

We are getting closer to “Her” (part 2!) Conversationally do anything with emails, using LLM chaining & few-shot prompting for tool use ( @LangChainAI inspired) This is now realtime (ish), thanks to #OpenAI gpt-3.5-turbo 🔈 on for voice realism! 🧵

75

462

3K

Last Seen Profiles

@ameliasweetcute

@BearMalluauh

@MaxDotBam

@FadiaWaheed_786

@danharralson

@ConfAscoliFermo

@martin_buhl

@Rozinapaul99744

@SalmanHashmi992

@LaiyzeFN

@UCINOFICIAL

@Sattarafridi101

@PacMarineExpo

@TheGayBoyShow

@ayaba_n_olorin

@BrendaXerotere1

@OndaCeroAlmeria

@qrsive

@SimaenagaEikyu

@afzNews

@VeruschkaLevels

@moehtaufiq

@Kayinl

@Ada_County

@dasorher

@KVenturo

@jyotikalasias

@Change__Lebanon

@DrSabaQamarKha1

@Elizabe79432029

@codeandstate

@asyunooekaki

@cardibarchive_

@GrupoCosentino

@ZhiZhuWeb

@FatimaTariq1920

@justLV

Justin Alvey

10 months

I “jailbroke” a Google Nest Mini so that you can run your own LLM’s, agents and voice models. Here’s a demo using it to manage all my messages (with help from @onbeeper ) 🔊 on, and wait for surprise guest! I thought hard about how to best tackle this and why, see 🧵

393

3K

15K

@justLV

Justin Alvey

1 year

I wanted to imagine how we’d better use #stablediffusion for video content / AR. A major obstacle, why most videos are so flickery, is lack of temporal & viewing angle consistency, so I experimented with an approach to fix this See 🧵 for process & examples

46

363

3K

@justLV

Justin Alvey

10 months

I’m working on open sourcing the PCB design, build instructions, firmware, bot & server code - expect something in the next week or so. If you don't want to source Nest Mini's (or shells from AliExpress) it's still a great dev platform for developing an assistant! Stay tuned!

Tweet media one

53

57

1K

@justLV

Justin Alvey

9 months

Here's one of my modded Google Nest Mini's using @OpenAI function calling to take notes & control 💡 I’m releasing all code & docs to get this exact demo running yourself, including: 💬 Messages 🏡 Home Assistant integration 📝 Note-taking

39

159

1K

@justLV

Justin Alvey

1 year

We are getting closer to “Her” where conversation is the new interface. Siri couldn’t do it, so I built an e-mail summarizing feature using #GPT3 and life-like #AI generated voice on iOS. (🔈Audio on to be 🤯with voice realism!) How did I do this? 👇

47

197

955

@justLV

Justin Alvey

10 months

I've been experimenting with multiple of these, announcing important messages as they come in, morning briefings, noting down ideas and memos, and browsing agents. I couldn’t resist - here's a playful (unscripted!) video of two talking to each other prompted to be AI’s from "Her

17

115

901

@justLV

Justin Alvey

10 months

After looking into jailbreaking options, I opted to completely replace the PCB. This let’s you use a cheap ($2) but powerful & developer friendly WiFi chip with a highly capable audio framework. This allows a paradigm of multiple cheap edge devices for audio & voice detection…

17

49

747

@justLV

Justin Alvey

2 years

1/ I created this with Stable Diffusion using image inpainting and “walking through the latent space” Without using tweening, every frame is generated by an interpolated embedding and variable denoising strength, so keeping continuity was tricky See 🧵for process

@karenxcheng

Karen X. Cheng

2 years

Testing out Stable Diffusion inpainting on a video - by @justLV See below for his process #inpainting #stablediffusion #artificialintelligence

124

2K

12K

14

122

671

@justLV

Justin Alvey

1 year

I used the #StableDiffusion 2 Depth Guided model to create architecture photos from dollhouse furniture. By using a depth-map you can create images with incredible spatial consistency without using any of the original RGB image. See 🧵

@karenxcheng

Karen X. Cheng

1 year

Using AI for design inspiration We used Stable Diffusion Depth to Image to get the consistency - collab with @justLV See below for our process #ArtificialIntelligence #stablediffusion #interiordesign

24

161

1K

6

126

609

@justLV

Justin Alvey

10 months

The custom PCB uses @EspressifSystem 's ESP32-S3 I went through 2 revisions from a module to a SoC package with extra flash, simplifying to single-sided SMT (< $10 BOM) All features such as LED’s, capacitive touch, mute switch are working, & even programmable from Arduino (/IDF)

Tweet media one

9

27

432

@justLV

Justin Alvey

10 months

& offloading large models to a more powerful local device (whether your M2 Mac, PC server w/ GPU or even "tinybox"!) In most cases this device is already trusted with your credentials and data so you don’t have to hand these off to some cloud & data need never leave your home

2

6

344

@justLV

Justin Alvey

10 months

For this demo I used a custom “Maubot” with my @onbeeper credentials (a messaging app which securely bridges your messaging clients using the Matrix protocol & e2e encryption) which runs locally serving an API I’m then using GPT3.5 (for speed) with function calling to query this

3

5

258

@justLV

Justin Alvey

1 year

I used AI to create a (comedic) guided meditation for the New Year! (audio on, no meditation pose necessary!) Used ChatGPT for an initial draft, and TorToiSe trained on only 30s of audio of Sam Harris See 🧵 for implementation details

12

37

211

@justLV

Justin Alvey

10 months

@dessy_ocean @onbeeper I’m considering different options for selling based on demand - mainly as a easy way to get them out there

28

0

204

@justLV

Justin Alvey

10 months

Fro the prompt I added details such as family & friends, current date, notification preferences & a list additional character voices that GPT can respond in. The response is then parsed and sent to @elevenlabsio

5

5

202

@justLV

Justin Alvey

1 year

Here are some more out there takes, including turning my couch into a jumping castle! 🏰🎈 There are endless possibilities here for content creation. Follow for more creative AI experiments!

7

7

142

@justLV

Justin Alvey

7 months

@OpenAI I've made the project orderable from @PCBWayOfficial directly, and updated the Github with the Altium design files. Enjoy!

Tweet card media

Onju Voice - AI assistant replacement to Google Nest Mini by @justLV - Share Project - PCBWay

READ THIS FIRST:This isn't a finished product, nor will I be making it one. I'm sharing this as many were interested in hacking on this further - if you're not comfortable tinkering on software,...

17

8

136

@justLV

Justin Alvey

1 year

Once the "atlas" was learned I could then run it through #depth2img , then use the new atlas to reproject across the video. This last remapping part is quick so you could imagine it being rendered live based on your viewing angle for #AR (for a pre-generated scene)

3

6

103

@justLV

Justin Alvey

1 year

Imagine just speaking and waving your cursor to have a personalized AI assist you in any app Here’s a quick demo of using voice, my cursor gestures & what's visible on-screen to prompt an #LLM agent (with access to my calendar & preferences) (🔊 on for voice prompts!) 🧵

8

11

105

@justLV

Justin Alvey

1 year

@LangChainAI This provides an incredibly natural way of searching for emails & then referencing them “are there any unread emails mentioning X in the last month?” “tell me more about the last one” “who else was cc’d on the picnic one?” “reply to the one about X saying …” another e.g.:

5

14

99

@justLV

Justin Alvey

2 years

A Neural Radiance Field ( #NeRF ) lets you create unique viewpoints you couldn’t otherwise - here’s a great example of creating a drone shot from frames pulled from a camera video. Details follow...

@karenxcheng

Karen X. Cheng

2 years

1/ Now you can create "drone" shots from your phone footage, thanks to NeRF Collab with @justlv / software @nerfstudioteam / see below for our process #NeRF #neuralrendering #artificialintelligence #instantNeRF

83

1K

7K

5

17

102

@justLV

Justin Alvey

2 years

6/ Not all walks through the latent space were a smooth path, but it’s easy to script it to find pairs that work well (and let your GPU replace your central heating) Having the ability to play with these models on this level is incredible. More creative AI experiments to come!

2

5

94

@justLV

Justin Alvey

1 year

I’ve been building @onjuai , a tool that makes it incredibly natural to interact with computers Make conversational requests, powered by LLMs & the context of the app you’re in, without breaking your flow Here’s a first example of using it with... Terminal! (🧵 for access)

5

15

95

@justLV

Justin Alvey

1 year

Ideally you want to learn a single representation of an object across time or different viewing directions to perform a *single* #img2img generation on. For this I used (2021)

1

8

92

@justLV

Justin Alvey

10 months

@MatiVivorita @onbeeper Alan Watts - but I’m referencing this

Tweet card media

Her - Alan Watts scene

www.youtube.com

4

4

86

@justLV

Justin Alvey

1 year

I used the Gmail API to feed in recent unread e-mails into a prompt and send to the @OpenAI #GPT3 Completion API. Calling out details such as not “just reading them out” and other prompt tweaks gave good results

Tweet media one

2

4

85

@justLV

Justin Alvey

1 year

The authors of the paper recommend using Mask R-CNN for creating a segmentation mask before training, but for this I found it easier (and cleaner) to just create a mask with the Rotobrush in After Effects

1

6

70

@justLV

Justin Alvey

1 year

The audio model was fine-tuned on speech from the movie Her. I got good results with TorToiSe, but have also experimented with ViTS & YourTTS from @coqui_ai and more recently @ElevenLabs . None are fast enough for a snappy response together with da-vinci-003 completions, so...

6

7

71

@justLV

Justin Alvey

5 years

How to make the neural lace a reality, and why we need to push BCI development #schoolofai

3

19

63

@justLV

Justin Alvey

1 year

It’s an incredible time to be building interactive experiences. (Unposted) voice experiments I've been running are smart home control from Pi's, a morning chat briefed with my daily priorities, events, weather, sleep data etc. See my profile for other creative AI experiments

9

2

62

@justLV

Justin Alvey

10 months

@dessy_ocean @onbeeper Quick update: I've made some PCB improvements for WiFi performance etc. including making 4-layer (should have done this sooner) & ordered a batch to validate Meanwhile I applied to list this on @crowd_supply & also following up with @seeedstudio & others. So stay tuned! 🙏

Tweet media one

Tweet media two

Tweet media three

8

4

62

@justLV

Justin Alvey

1 year

@colinfortuner This uses @elevenlabsio , but tbh feel I can't release this wider for folks until there is a good open source option - lack of good data privacy makes me uncomfortable recommending people send all their actual e-mail summaries to them. I have hopes for …

Tweet card media

How to Pretrain on LibriTTS · Issue #24 · enhuiz/vall-e

Hi, Its great to see the implementation of a recent work and appreciable. I was able to setup the training with custom data for single speaker. Following are some of the queries: What is the sample...

4

6

60

@justLV

Justin Alvey

1 year

I imagined how I might ask questions about my books, without the distraction of taking out my phone Here's an experiment using #GPT4 on a Kindle with a voice request through an @Apple HomePod

3

6

57

@justLV

Justin Alvey

2 years

5/ Some tricks were required with blending and adjusting the inpainting mask to smoothly switch over the init images of the two real phones (example generations on the right)

1

3

55

@justLV

Justin Alvey

1 year

Native iOS integration was done through Shortcuts, see this thread for how I did this previously

@justLV

Justin Alvey

1 year

We are getting closer to “Her” where conversation is the new interface. Siri couldn’t do it, so I built an e-mail summarizing feature using #GPT3 and life-like #AI generated voice on iOS. (🔈Audio on to be 🤯with voice realism!) How did I do this? 👇

47

197

955

1

7

54

@justLV

Justin Alvey

2 years

4/ Transitions were done using a customized @huggingface 🧨Diffusers pipeline. This lets me “slerp” between both noise latents AND text embeddings, for each given seed & prompt respectively (while keeping denoising strength at ~0.8)

3

6

52

@justLV

Justin Alvey

2 years

2/ First off, finding the right combination of prompt, seed and denoising strength for an #img2img in-painting is a roll of the dice Luckily it is easy to script large batches to cherrypick

3

4

54

@justLV

Justin Alvey

1 year

@OpenAI Here are the settings I used, you can see how #GPT3 does a great job of conversationally summarizing. (For the sake of privacy I made up the e-mails shown in the demo)

Tweet media one

Tweet media two

2

4

50

@justLV

Justin Alvey

1 year

This learns an "atlas" to represent an object and its background across the video. Regularization losses during training help preserve the original shape, with a result that resembles a usable slightly "unwrapped" version of the object

Tweet media one

1

5

51

@justLV

Justin Alvey

1 year

2/ This model is unique as it was fine-tuned from the Stable Diffusion 2 base with an extra channel for depth. Using MiDaS (a model to predict depth from a single image), it can create new images with matching depth maps to your "init image"

Tweet media one

1

5

51

@justLV

Justin Alvey

10 months

@58mitchs @onbeeper Thanks! This next week or two I’m working on cleaning up design files and creating some good docs

6

0

48

@justLV

Justin Alvey

5 years

Hacked together a pair of wide-angle cameras onto a home-made rocket so that I could say I've built & launched a rocket from NASA... The landing could use some work but re-usability is in the bag 🚀♻️ @NASAAmes

0

1

24

@justLV

Justin Alvey

5 years

Entrancing demo of Optical image stabilization in action by ⁦ @panasonic ⁩ ⁦ @lx5 ⁩ #CES2019

0

0

20

@justLV

Justin Alvey

6 years

Thanks @foundersfund , we now finally have our flying cars we were promised. @SpaceX you captivated and inspired millions 🚀🙌

Tweet media one

0

0

18

@justLV

Justin Alvey

2 years

3/ The first and last pairs were just regular #img2img ramped through a range of denoising strength of 0 to 0.8

1

3

37

@justLV

Justin Alvey

1 year

What worked best for me was putting the prompt and few-shot examples in the “system” message, and getting the assistant to think it is providing the command to the user, who will then query the API and return results to the assistant to summarize (see e.g.)

Tweet media one

2

2

34

@justLV

Justin Alvey

1 year

It is pretty surreal seeing e-mail replies coming in before the voice response is generated.

Tweet media one

Tweet media two

2

1

35

@justLV

Justin Alvey

1 year

Voice transcription runs on device using the app name & selected text for context which gives it incredible accuracy. See the previous demo using Terminal

@justLV

Justin Alvey

1 year

I’ve been building @onjuai , a tool that makes it incredibly natural to interact with computers Make conversational requests, powered by LLMs & the context of the app you’re in, without breaking your flow Here’s a first example of using it with... Terminal! (🧵 for access)

5

15

95

1

2

37

@justLV

Justin Alvey

1 year

3/ I set the denoising strength to 1.0 so that none of the original RGB image was used Even with widely different prompts it was able to generate consistent objects Using simple, recognizable shapes such as wooden doll-house furniture worked great for this

Tweet media one

3

2

36

@justLV

Justin Alvey

1 year

@fffiloni @huggingface I'd be happy to help guide if someone more experienced with this wants to set one up! Currently learning an "atlas" takes some time (I left it overnight but it probably converges to something usable sooner). This is just an MVP of the ideal case - which would be to scan your…

4

0

34

@justLV

Justin Alvey

1 year

5/ Here are a few of the prompts used: "A beautiful rustic Balinese villa, architecture magazine, modern bedroom, infinity pool outside, design minimalism, stone surfaces"

Tweet media one

3

2

34

@justLV

Justin Alvey

5 years

Showing off some cobot moves! 🤖🕺 A tactile telerobot collaboration between @shadowrobot @syntouchinc @haptx at #reMARS

0

4

27

@justLV

Justin Alvey

2 years

@NVIDIAAIDev Here is the same scene shown in Instant NGP. While @nerfstudioteam is missing some features of Instant NGP, being community-driven the rate of progress since their first launch a few weeks has been incredible to watch

2

2

26

@justLV

Justin Alvey

10 months

@silentlink1 @sulfuroid @onbeeper e2ee & megolm ftw! 🔐

3

0

25

@justLV

Justin Alvey

1 year

8/ There is some “creativity” in how the depth-map is matched under the prompt. Here are a few outtakes where the model tried to match the plant to antlers, toys, candles, statues, a double-necked guitar and even a kid with Mickey ears🤯 Follow for more creative experiments 👨‍🎨

Tweet media one

1

1

22

@justLV

Justin Alvey

1 year

4/ Regular photos ended up having an unavoidable “doll-house” feel to them (even with heavy prompt tweaking) due to the extreme perspective. I found that changing to a longer focal length (3x on an iPhone) and capturing from further away resolved this.

Tweet media one

2

2

21

@justLV

Justin Alvey

10 months

@ekryski @adafruit Yep, I want to fix all the long tail issues with the PCB before releasing - avoiding wasting a lot of time debugging. Aiming to finish revisions in the next week. Mostly interested in getting people experimenting with what they’d like to see built!

1

0

21

@justLV

Justin Alvey

1 year

7/ "Retro bedroom studio, arcade, 80's style, vintage framed posters, trending architecture magazine, rugs, metal industrial pipes, murals, guitars and sound equipment, grunge, concrete floor"

Tweet media one

1

1

20

@justLV

Justin Alvey

1 year

Beyond the above digital minimalism, I’ve spent a lot of time imagining what a LLM reading experience might look like, especially for fiction Imagine pausing a book, and talking to characters at that moment, or unhurriedly exploring the scenes that the author has vividly crafted

2

1

17

@justLV

Justin Alvey

10 months

@shrimpyuk @onbeeper @RemindMe_OfThis The pressure is on!! ⏳🤣 Here's a quick update

@justLV

Justin Alvey

10 months

@dessy_ocean @onbeeper Quick update: I've made some PCB improvements for WiFi performance etc. including making 4-layer (should have done this sooner) & ordered a batch to validate Meanwhile I applied to list this on @crowd_supply & also following up with @seeedstudio & others. So stay tuned! 🙏

Tweet media one

Tweet media two

Tweet media three

8

4

62

3

0

18

@justLV

Justin Alvey

1 year

An underlooked angle on why  @Apple Reality (AR) could be relevant is Iris scanning and “Proof of Personhood” for digital spaces. We’ve seen an explosion in #AI Agents, generative capabilities & increasingly realistic speech, not counting Twitter’s existing bot problems. 🧵

Tweet media one

Tweet media two

2

1

18

@justLV

Justin Alvey

1 year

3 email commands are learned (which are then formatted into a GMail API request): - search for emails with params, giving a list of email snippets indexed so the LLM can refer to in further requests - get the full e-mail by index - reply to an e-mail by index with a response

1

2

15

@justLV

Justin Alvey

1 year

@wakingup Diffusion models & autoregressive transformers are coming for audio! Text-To-Speech was created using I also highly enjoyed reading the author's blog

Tweet card media

GitHub - neonbjb/tortoise-tts: A multi-voice TTS system trained with an emphasis on quality

A multi-voice TTS system trained with an emphasis on quality - neonbjb/tortoise-tts

3

0

17

@justLV

Justin Alvey

7 years

The best way to survive the #sfheatwave with @snap @spectacles #swimming #ocean #sunset

0

3

17

@justLV

Justin Alvey

1 year

@justinliang1020 @bentossell @LangChainAI See thread

@justLV

Justin Alvey

1 year

@colinfortuner This uses @elevenlabsio , but tbh feel I can't release this wider for folks until there is a good open source option - lack of good data privacy makes me uncomfortable recommending people send all their actual e-mail summaries to them. I have hopes for …

4

6

60

1

1

15

@justLV

Justin Alvey

1 year

I originally manually chained responses, keeping track of and pruning history to feed into the next chain, and using stop tokens to prevent the LLM from hallucinating the API response. There was some refactoring & experimentation to make use of the new chat completions API...

1

1

14

@justLV

Justin Alvey

7 years

I did a teardown of the @nest #NestThermostatE . Respect the new design direction & hats off to the engineering team 🙌

Tweet card media

Nest Thermostat E teardown, and on making beautiful devices for the home

Just 3 days ago, Nest launched their latest Nest Thermostat E. It appeared to try take two bold steps: to take a refreshing new design…

justlv.medium.com

3

1

16

@justLV

Justin Alvey

1 year

6/ "Luxurious modern studio bedroom, trending architecture magazine photo, colorful framed art hanging over bed, design minimalism, furry white rugs, trendy, industrial, pop art, boho chic"

Tweet media one

1

2

13

@justLV

Justin Alvey

1 year

@colinfortuner @elevenlabsio There are efforts to speed up TorToiSe, but it's inherently an approach that is still too slow for realtime (~1min) I fine-tuned YourTTS with an hour of this voice - results were fast & decent but not nearly as expressive and still had phoneme errors.

Tweet card media

GitHub - 152334H/tortoise-tts-fast: Fast TorToiSe inference (5x or your money back!)

Fast TorToiSe inference (5x or your money back!). Contribute to 152334H/tortoise-tts-fast development by creating an account on GitHub.

1

1

12

@justLV

Justin Alvey

1 year

I believe the magic happens when you pair 🍐 voice (for rich requests & feedback) with physical inputs (for shortcuts & confirmation) to get the answer where you need it (More demos in different apps coming!) Sign up for access at !

1

0

11

@justLV

Justin Alvey

6 years

Teardown of the @amazonecho Dot (3rd gen) shows some impressive cosmetic and speaker improvements, but I couldn't find where #Alexa was hiding...

Tweet media one

1

0

11

@justLV

Justin Alvey

2 years

@NVIDIAAIDev @nerfstudioteam This is just scratching the surface, stay tuned as I'll be posting lots more experiments soon!

1

1

10

@justLV

Justin Alvey

11 months

@amasad Wouldn't that be 0.7568359375? (assuming fp16) Eagerly awaiting the rest...

0

0

9

@justLV

Justin Alvey

1 year

ChatGPT came up with some creative ideas, but the delivery was still fairly vanilla, so I iterated on it heavily and added a few Sam-isms from my experience with the @wakingup app (Jokes aside - highly recommended)

Tweet media one

1

0

9

@justLV

Justin Alvey

1 year

@wakingup I split up text into short chunks to create the most natural flow, then did a grid search across multiple parameters to find the most realistic copy of Sam's mannerisms Each sentence takes about 2-3 minutes to generate on a 3090, and I generated ~20 for each to cherrypick

1

0

8

@justLV

Justin Alvey

9 months

@hypnagogica @TheRealAdamG @OpenAI

@justLV

Justin Alvey

10 months

I “jailbroke” a Google Nest Mini so that you can run your own LLM’s, agents and voice models. Here’s a demo using it to manage all my messages (with help from @onbeeper ) 🔊 on, and wait for surprise guest! I thought hard about how to best tackle this and why, see 🧵

393

3K

15K

0

0

7

@justLV

Justin Alvey

2 months

@erhartford @JeflonZuckgates @onbeeper It is, albeit a bit out of date on the LLM/TTS side

Tweet card media

GitHub - justLV/onju-voice: A hackable AI home assistant platform

A hackable AI home assistant platform. Contribute to justLV/onju-voice development by creating an account on GitHub.

1

1

8

@justLV

Justin Alvey

7 years

Excited for latest book from @bunniestudios ! 🎉 Now's the best time to start knowing our devices before they know us 👨‍💻🤖

Tweet media one

0

0

6

@justLV

Justin Alvey

1 year

Finding the right reference material is critical (quality over quantity) so I used 3 carefully edited clips of <10s each. Tricks with prompt engineering is also possible - the content influences the generated audio intonations

1

0

7

@justLV

Justin Alvey

1 year

While  already has hardware verification with their Secure Enclave chip & “hardware root of trust”, an AR headset with iris scanning and liveness detection would ensure a 1:1 mapping of human to device

Tweet media one

Tweet media two

1

0

7

@justLV

Justin Alvey

1 year

Right now this just uses on-screen text, but it is easy to imagine this with multi-modal models (actively experimenting) and even other hardware form factors (😲🤫)

1

0

7

@justLV

Justin Alvey

10 months

@JimmyBrumant Voice Activity Detection for filtering out spoken phrases, Whisper for STT running on my Macbook / Linux server (depending), and using the "no speech prob". If you were asking about TTS, using Elevenlabs - tbh best out there for voice cloning (for now...)

3

1

7

@justLV

Justin Alvey

1 year

Responses are currently using GPT4, chained when needed with memory, preferences & integrations. Although it can provide highly specific answers, it works across all apps w/o extensions needed for each & allows credentials for integrations to be centrally & securely managed

2

0

6

@justLV

Justin Alvey

9 months

@guru154929 @OpenAI Take a look at the readme and code. This uses timeouts to only listen after responses or when the device first turns on or is tapped, and when the mute switch is not flipped. Of course wakewords can be used but wouldn’t make as good conversation or demo clearly. But critically,…

0

0

6

@justLV

Justin Alvey

7 years

👌 @nest 's new thermostat. Exactly how I'd design a smarthome device: subtle ceramic-feel, to blend in. Or did I? 😉

2

2

6

@justLV

Justin Alvey

1 year

Lastly, yes, the headset will be 💰 initially, but 1) I’d expect this to set a precedent of HW verification for other devices & mfg'ers 2) this is (relatively) small change compared to other "flexes of fungibility" for the digital world (NFT's)

1

0

5

@justLV

Justin Alvey

2 years

What if Spot from @bostondynamics was not a dog, but actually a wise dragon or friendly brontosaurus? #stablediffusion #img2img

Tweet media one

Tweet media two

Tweet media three

0

0

5

@justLV

Justin Alvey

1 year

It's actually incredibly simple: When I hit the shortcut to start voice recording, it captures the current window and uses Apple's Vision framework to perform OCR on all the text. This takes about 1-2 seconds but runs in parallel to voice recording

2

0

5

@justLV

Justin Alvey

10 months

@rhasspy @IgorAntarov @onbeeper @home_assistant Yep, it uses I2S for the 2 mic's & speaker. I'm an advocate for offloading to a local GPU / "secure enclave" w credentials for my applications, but you can do whatever you'd like with it!

2

1

5

@justLV

Justin Alvey

2 years

The great handling of unbounded scenes like this one is thanks to spatial distortion (as proposed in Mip-NeRF 360 paper) where any point beyond a unit sphere (from 1 to ∞) is mapped to into a second sphere (from 1 to 2). allow the network to learn beyond a scene beyond a cube

Tweet media one

1

0

5

@justLV

Justin Alvey

9 months

@58mitchs @onbeeper Update over here

@justLV

Justin Alvey

9 months

Here's one of my modded Google Nest Mini's using @OpenAI function calling to take notes & control 💡 I’m releasing all code & docs to get this exact demo running yourself, including: 💬 Messages 🏡 Home Assistant integration 📝 Note-taking

39

159

1K

1

1

5

@justLV

Justin Alvey

1 year

Transcription has to be fast & flawless for a good UX. To do this the model runs on-device and is conditioned on the app you’re in and with previous commands or messages to ensure accuracy with ambiguous words. (Recordings never need to leave your device)

1

0

5

@justLV

Justin Alvey

5 years

@munchery I'm guessing these are even more rare today?

0

0

4

@justLV

Justin Alvey

1 year

This demo uses Siri & shortcuts to send the question to a server. It uses Kindle's built in browser to load a formatted page with JavaScript to fetch updates as the response from @OpenAI is streaming. The browser is really limited so I had to keep it minimal and stick to ES5

1

1

3

@justLV

Justin Alvey

9 years

Conquered Twin Peaks easily thanks to @FaradayBikes . This is how traversing SF on a bike should be done! http://t.co/ZJXLe9Ub02

Tweet media one

2

1

4

@justLV

Justin Alvey

10 months

@comigor_ @dessy_ocean @onbeeper @crowd_supply @seeedstudio That's up next - but wanted to get the hardware revisions kicked off first...

1

0

4

@justLV

Justin Alvey

7 years

Disembodied voice assistants talking to each other 🤖🤖😱 #googlehomemini #AmazonEcho #alexa #OKGoogle

0

0

4

@justLV

Justin Alvey

2 years

Nerfstudio is a great platform for experimenting with the latest research breakthroughs in NeRF’s, co-created by one of the author’s of the original paper, . Here are some examples of features they’ve rolled into their de facto model:

NeRF: Neural Radiance Fields

A method for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views.

www.matthewtancik.com

1

1

4

@justLV

Justin Alvey

7 years

I did a teardown of the new Google Home Mini @madebygoogle A beautifully designed & neat little product @micahtc ! 🍩

Tweet card media

Google Home Mini teardown, comparison to Echo Dot, and giving technology a voice

Google just announced some new products — one of which was the Google Home Mini, a smaller, cheaper version of their voice assistant, which…

justlv.medium.com

0

1

4