louis030195 @louis030195 Twitter profile

Pinned Tweet

louis030195

@louis030195

8 days

did over 20k contributions on @github what about you?

0

1

7

Last Seen Profiles

@chinaunicom

@Dreamvilliann90

@tzubmi

@JujuliaGrace

@AnovaLlp60900

@AubrieShur85567

@jandakembangstw

@aitokyouki

@tayyshmu_

@iam_oladino

@annbrandCOMM

@BSrkalovic23136

@booublik

@chiko0530723669

@wxou

@MissyRenee325

@BlazoElixir

@Bullet4Justice

@vHJWiXSM9282140

@icthicmagazine

@annieandersonnn

@Craig633680731

@DecayingTeeth

@Fabiana84220713

@FreezyFood

@ZSBT9

@BrianSm71994635

@Thomas999957630

@detlnovelas1

@takinzj

@tto_ling

@Bigbaddaboom7

@ArroyoAngel3

@GueguenFrancoi2

@bucksturfphil

@realzizz

louis030195

@louis030195

10 months

ai insights to optimize cognition, focus, and mental performance 🧠 data @neurosity x ❤️😴 data @ouraring x @Apple watch x 🤖 = 🥦🧠💪 cc @_buildspace @_nightsweekends @FarzaTV

16

0

44

louis030195

@louis030195

10 months

today I built an app that logs my emotions in my notes throughout the day based on my brainwaves @neurosity @obsdmd

4

39

louis030195

@louis030195

9 months

i built a #fitness , #health , and #wellness ai assistant in @WhatsApp spend 10x less time on @ouraring @ChooseMuse @WHOOP etc. apps while getting 10x the benefits dm for exclusive access

6

4

32

louis030195

@louis030195

6 months

i built an open source version of OpenAI Assistants API it's compatible with any LLM & embeddings model and u can swap it out for OpenAI assistants API with just one line of code. if you want this let me know 👇

7

1

28

louis030195

@louis030195

5 months

Had an epic evening with 52 brilliant hackers! 🚀 Thanks to the Assistants API, we went from idea to execution in less than 90 minutes, a task that once took so many days! Want to reduce your AI development costs by 1000x? Check out projects and our link below! 👇

4

2

26

louis030195

@louis030195

6 months

Mistral 7b + OpenAI API = 🔥 just released an example of using Mistral 7b (one of the best open source LLM) with an open source version of OpenAI Assistants API OpenAI Assistants API is truly amazing - it automates decision making in your product ⭐️ 👇

4

1

22

louis030195

@louis030195

1 year

Embedbase cloud now uses @supabase ! Get your embeddings-powered app off localhost in minutes at

3

4

20

louis030195

@louis030195

4 months

👁️ a Monocle that can record everything happening in your life @brilliantlabsAR

0

2

17

louis030195

@louis030195

10 months

just added insights from @AnthropicAI about your brain health through @neurosity 's brain-computer interface wear the Crown, record your focus, add tags, get insights, get better, weekly FYI: Neurosity Crown collect your brain electrical activity cc @_buildspace 👇

4

0

19

louis030195

@louis030195

1 year

Using @AiEleuther GPT-J-6B in @Apple Shortcut with @huggingface API 🧙 A little plumbing between a few LLMs and you can imagine some value?

0

3

18

louis030195

@louis030195

10 months

just shipped an @ouraring integration @neurosity + @ouraring + AI = striking insights about what affects your sleep and focus level throughout the days soon you will know what events affects your anxiety according to your brainwaves and HRV 👇

4

0

18

louis030195

@louis030195

10 months

just launched an app that let you become a better version of yourself based on your brain data get insights on your life, what does good to you, what's harmful based on your electrical brain activity from the amazing @neurosity wearable 👇

2

4

17

louis030195

@louis030195

1 month

common techbros' mistake: thinking that funding or accelerator is the goal don't waste your energy on investors, focus on creating something useful and surviving investors will be knocking on your door soon enough

1

0

11

louis030195

@louis030195

11 months

Using LLMs to execute the right SQL query to solve a user's problem 100 lines of js code Link to replit 👇

4

0

12

louis030195

@louis030195

6 months

OpenAI Assistants API for any LLM - open source one liner away from switching from openai atm supports @AnthropicAI but could easily supports any open source LLM github link 👇

louis030195

@louis030195

6 months

i built an open source version of OpenAI Assistants API it's compatible with any LLM & embeddings model and u can swap it out for OpenAI assistants API with just one line of code. if you want this let me know 👇

7

1

28

4

0

13

louis030195

@louis030195

9 months

@ChanLPfa is a smoker even considered alive?

1

0

11

louis030195

@louis030195

1 year

A lot of learning, thanks a lot for the dedication @_buildspace ❤️

0

12

louis030195

@louis030195

6 months

🤖 use OpenAI Assistants API with your own models in your own infra one liner to use open source LLMs with OpenAI Assistants API 0 data leaked to openai link 👇

3

0

12

louis030195

@louis030195

5 months

🧑‍💻 I'm organizing a hack night focused on the new OpenAI Assistants API This API enables building AI apps 10 times faster In less than two hours, we'll create an app using the Assistants API I'll also show how to switch to open-source LLMs w a single line of code. 👇

3

1

10

louis030195

@louis030195

9 months

introducing Coconut Combinator (unrelated to @ycombinator ) a 1-3 months exploration / exploitation marathon for ambitious, curious, and inviting individuals from a beautiful villa on an island in Thailand included: massage, cook, beach, adventure, top-notch ideas 👇

2

0

10

louis030195

@louis030195

17 days

most people think there are 3 space companies on earth, actually there are thousands now and it's nonlinear with @SpaceX cutting cost for bringing mass-to-orbit by thousands

2

10

louis030195

@louis030195

7 months

soon we'll have LLMs that interact with hardware directly no operating system - just bits - 0 and 1

2

0

10

louis030195

@louis030195

17 days

death is maximum entropy, the end state of every system in the universe. but here's the thing - the choices you make today can have a profound impact on how quickly that entropy takes hold. think about it this way: every time you opt for comfort over challenge, every time you

2

1

10

louis030195

@louis030195

4 months

planning is overrated, sometimes the best outcome come from just keep doing what you love "you can't connect the dots looking forward; you can only connect them looking backward" - Steve Jobs

1

0

9

louis030195

@louis030195

10 months

i just created an app that saves my brain electrical activity from @neurosity to the permanent web @ArweaveEco the human brain is the most complex object in the universe, and it's unfortunate that we don't keep track of our daily experience 👇 code

1

2

9

louis030195

@louis030195

7 months

confidence > competence thoughts?

3

0

8

louis030195

@louis030195

7 months

@fchollet Disagree Many people have high ambition but don't know how to find the right path to the top of the mountain

0

7

louis030195

@louis030195

1 year

Ask Questions to your GitHub repository and get exact answers One click and it's deployed on @vercel :) powered by @OpenAI , and embedbase!

3

8

louis030195

@louis030195

1 year

🚀 shipped a one-click deployment of embedbase

3

2

8

louis030195

@louis030195

1 year

llms are just lazy piece of s****

1

0

8

louis030195

@louis030195

4 years

@naval @DaStockPreacher "Truth is a pathless land." Krishnamurti

0

8

louis030195

@louis030195

6 months

LLM devs' biggest mistakes: - one-shot user interface (instead of a human iterative process in the loop, e.g. Figma) - too much, harmful abstractions (e.g. LangChain, bad hard-coded prompts that can't be modified) - too little context - no streaming - under-use of LLMs (use

1

8

louis030195

@louis030195

5 months

RAG is just the tip of the AI iceberg ✨ The new OpenAI Assistants API combines RAG, function calls, code interpretation - LLMs now perform complex calculations. AI apps that use Assistants API are 10x better If you're not using Assistants API you're lagging behind

3

2

8

louis030195

@louis030195

10 months

are you in control of your attention? introducing 🧠^🤖 = mediar, google maps for your brain health own an @Apple watch or @ouraring ? mediar let you keep tracks of your brain health quit autopilot, become focused, beat distractions, achieve flow state 👇

2

0

7

louis030195

@louis030195

10 months

just added the ability to tag your brain states track your brain health using @neurosity , tag, get insights, get better, weekly 👇

2

1

7

louis030195

@louis030195

15 days

i'd pay $2000 for a device that wrap my head like astronaut suit at night and give these feats: - 100% noise isolation - best air possible - best temperature - comfortable enough to sleep with it - less than 2 kg, easy to carry

1

0

6

louis030195

@louis030195

1 year

I created an AI clone of the philosopher Jiddu Krishnamurti

4

1

7

louis030195

@louis030195

6 months

i'm neither e/acc, nor ea, nor k/acc, nor w/e ... men are desperate for prescriptions true philosophy is forged from the ground up - without relying on authority

0

1

7

louis030195

@louis030195

9 months

top 6 tools that 1000x your 🧠in tech in 2023: - @obsdmd - @perplexity_ai - @vercel & AI playground (w @AnthropicAI & @OpenAI ) - from @amanrsanger - @supabase - @RewindAI

0

7

louis030195

@louis030195

19 days

the government is the bottleneck of our civilization

0

1

8

louis030195

@louis030195

10 months

i built iCloud for your mind it uses brain wave data from @neurosity Crown to save my memories forever interested in saving ur memories? 👇

5

2

7

louis030195

@louis030195

5 years

@woj_zaremba + Read books

1

0

7

louis030195

@louis030195

5 months

space is the new internet @anaprosina

Alder

@alder_riley

5 months

The future of the space industry in SF is bright. If you're in the city tonight swing by the @Interval or follow @StepsLeaps to be invited to the next one.

2

1

38

0

1

6

louis030195

@louis030195

1 year

"Create a react snippet that implements gnosis safe with wagmi?" Had so much fun playing with the Embedbase #GPT4 playground, so added the ability to talk to multiple data sources! This example is using @wagmi_sh and @safe

0

1

6

louis030195

@louis030195

5 months

startups life cycle you're either too early, on time, or too late in the market

1

6

louis030195

@louis030195

2 months

Skills generate compounding luck

1

0

6

louis030195

@louis030195

2 months

how the world works

0

2

louis030195

@louis030195

11 months

@mayowaoshin Seems like the only missing block to turn LLM into a 100% programming language is to combine with traditional CS algorithms, data structures and pure logic

3

1

6

louis030195

@louis030195

8 months

just as google maps makes you unable to navigate by yourself, chatgpt makes you unable to think independently

2

0

6

louis030195

@louis030195

1 year

It takes so much time & money to organize information across all the software we use. Time to get rid of everything, including the browser, and switch to #AI -augmented @obsdmd , let the magic of #AI organize information automatically for you.

Take messy notes and make them clear (jotting is the future of note taking)

Recently read “The end of organizing” and got me thinking how we could make note-taking more efficient using AI. In that spirit, here are a couple of things, I’ve tried with the AI assistant AVA...

forum.obsidian.md

1

4

louis030195

@louis030195

1 year

🖼️ Super excited to finally open-source the embedbase dashboard.

1

6

louis030195

@louis030195

5 months

when i arrived in sf i thought people had interesting ideas the truth is even here groupthink is the norm

1

0

6

louis030195

@louis030195

10 months

@FarzaTV @_buildspace glad to be here :)

1

0

6

louis030195

@louis030195

8 months

in the near future we'll have 10 LLMs on the client interacting with 10 other LLMs on the server, just as many models interact with each others in the brain

1

0

6

louis030195

@louis030195

5 months

it’s almost 2024 and we’ve got a few gigabytes file smarter than most animals on earth that took millions of years to evolve vs a few days of training

mistralai/Mixtral-8x7B-v0.1 · Hugging Face

huggingface.co

0

6

louis030195

@louis030195

10 months

r u in sf and wanna hack on brain computer interfaces? just organized an event on wednesday 👇

1

6

louis030195

@louis030195

6 months

science fiction used to predict technology, now technology predicts science fiction

0

1

6

louis030195

@louis030195

7 months

@ylecun the most important scientists of the decade

0

6

louis030195

@louis030195

7 months

@naval Moving from top tech eu cities to SF feels like taking a time machine and go 50 years in the future

1

0

4

louis030195

@louis030195

4 months

I'm still waiting for the real web 3: 2d or 3d infinite canvas powered by AI. What we've learned from brain-computer science is that every brain has very different patterns. That's why the next web will adapt to each brain and more closely resemble our evolutionary environment.

1

0

5

louis030195

@louis030195

8 months

031023 framework to find general information (non code) what's yours?

4

0

5

louis030195

@louis030195

9 months

a few months ago i interrupted several years of zero carb diet: there are too many inputs in the equation, ppl say go carn, go vegan, go x, y, fast, cold showers, take pills w/e “The first principle is that you must not fool yourself and you are the easiest person to fool.”

1

0

5

louis030195

@louis030195

5 months

UX is 10x more important in application layer AI product than in non-AI product LLMs are a lever on human intelligence and if you fail on the fundamentals it has a nonlinear impact Great UX: - @cursor_ai - @perplexity_ai - @RewindAI

0

5

louis030195

@louis030195

2 months

Just updated Software 3.0 website, lmk your thoughts

0

4

louis030195

@louis030195

1 year

Get latest @OpenAI #ChatGPT model in @obsdmd No context switching, drop all your software, feed all your life context & get your brain supercharged by ChatGPT

1

0

5

louis030195

@louis030195

4 months

What's the best equivalent of a smartphone but without screen, hackable (e.g. Linux), discreet, durable (6h hours), internet-ready, end-to-end? Basically a server in your pocket? Or if possible as an implant :P

0

3

louis030195

@louis030195

1 year

When prompting a language model, biological or artificial, the output is as good as the input. In other words, good question, good answers.

1

0

5

louis030195

@louis030195

7 months

I'm a bit skeptical about "Scaling Reinforcement Learning from Human Feedback with AI Feedback" The point of RLHF is to align AI to human. If you use an AI to align a new AI there is a higher risk of ending up with a paperclip maximizer, a disobedient AI

RLAIF: Scaling Reinforcement Learning from Human Feedback with AI Feedback

Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models (LLMs) with human preferences. However, gathering high-quality human preference labels can...

arxiv.org

0

5

louis030195

@louis030195

7 months

I’ve been using embeddings with LLM since 2020 in production and yes, embeddings are overkill Just using full text search and generating the queries with LLM will remove a ton of infra headaches If it’s too slow, use a small LLM for it. I.e like speculative generation

2

0

4

louis030195

@louis030195

3 months

new personal knowledge management system I'm experimenting (in parallel to @obsdmd daily note) using @excalidraw Basically infinite canvas on a specific topic, just adding a box daily Anyone experimenting on daily PKM in infinite canvases?

0

1

3

louis030195

@louis030195

6 months

2/ you could use it with @AnthropicAI , @cohere , @scale_AI , @modal_labs , @huggingface , @replicate In Rust, production-ready, one-click away to your infra lmk if you want it, will drop the link 🙂 Stay in touch:

Join the HAL-9100 Discord Server!

Check out the HAL-9100 community on Discord - hang out with 62 other members and enjoy free voice and text chat.

discord.com

2

0

4

louis030195

@louis030195

1 year

I think very few people yet understand that LLM are a new programming language. What you can do in 5000 lines of C, you can do in 500 lines of JS, you can do in 50 lines of #OpenAI GPT3.

1

5

louis030195

@louis030195

1 month

The herd mentality in AI engineering—jumping onto every new trend or GitHub repo—is like being a billiard ball: predictable and controlled. Where are the first-principles thinkers?

3

0

5

louis030195

@louis030195

7 months

@naval unfortunately most people are addicted to weather-talks

0

4

louis030195

@louis030195

9 months

wear a mask for long enough and you become the mask

0

1

5

louis030195

@louis030195

10 months

@_buildspace got accepted time to ship

1

0

5

louis030195

@louis030195

1 month

publicly sharing the biggest mistakes I've made in recent years while working on my own startup: - not being focused enough - being too focused on the solution rather than the problem/user - spending too much time building and not enough time selling - letting myself be guided

2

0

5

louis030195

@louis030195

5 months

📞 Open source function calling Let your LLM do the right stuff in your product automatically - without being stuck in openai OpenAI Assistants API but with any LLM 👇

1

0

5

louis030195

@louis030195

5 months

OpenAI Assistants API but 75% cheaper, 23x faster, 100% data private I'm working on a benchmark between an open source version OpenAI Assistants API vs the real one Planning to compare @AnthropicAI vs @MistralAI vs @OpenAI for different tools, domains, etc. 👇 Want this?

1

0

5

louis030195

@louis030195

5 months

working on an ai bitcoin advisor it's to showcase an example using openai assistants api built an open source version of this api wanna contribute to this api? 👇 23 times cheaper, 75% quicker, totally data-private everyone can access it using the same api and sdk openai uses

2

1

4

louis030195

@louis030195

6 months

0

1

4

louis030195

@louis030195

1 year

After writing over 600,000 words on @obsdmd , I realized that my human memory is so limited and that this kind of software is on a good direction to expand our brain.

1

4

louis030195

@louis030195

2 months

Meditation is overrated Writing underrated

0

4

louis030195

@louis030195

9 months

Mediar - Product Information, Latest Updates, and Reviews 2024 | Product Hunt

M is an AI assistant that analyzes multi-modal health data from wearables and user input, then delivers personalized insights and recommendations through chat to optimize wellbeing and performance.

www.producthunt.com

1

0

4

louis030195

@louis030195

3 months

Rust is gaining popularity because learning to code with AI is easier than ever. Although Rust is more verbose than Python or TS, it saves time by catching errors at compilation, preventing crashes in user hands Also, we’re moving towards Software 3.0, where most code is English

1

0

louis030195

@louis030195

2 months

Are there any billion dollars companies that came out of a hackathon?

2

0

4

louis030195

@louis030195

1 year

As we've seen with #chatGPT which is merely a better UX of a model that is freely accessible for years, LLM/AI is mostly a UX problem.

0

4

louis030195

@louis030195

10 months

this is here fyi:

Mediar

LLM Infra for defense

mediar.ai

1

0

4

louis030195

@louis030195

14 days

there is a clear trend in software: ppl want to use a single interface not 1000 ones context switching all the time

0

4

louis030195

@louis030195

2 months

hot take: @excalidraw > @tldraw > @figma 🍿

1

0

4

louis030195

@louis030195

1 year

🚀 Time to ship the next generation of apps powered by embeddings. embedbase now supports @supabase as a backend Get started now

1

0

4

louis030195

@louis030195

6 months

five years ago I trained AIs that would compete against each other for survival just for fun it was using similar algorithm than ChatGPT, reinforcement learning m herbivorous vs carnivorous carnivorous species seems always winner in history

Evol 0.0.2 - Unity Reinforcement Learning

Recorded on Androidhttps://github.com/louis030195/Evol

www.youtube.com

0

4

louis030195

@louis030195

8 months

@FurqanR Humans are converging towards a centralized, ant-like intelligence

0

2

louis030195

@louis030195

7 months

Big congrats to @anaprosina , selected as one of @payloadspace 's 30 under 30 Pioneers! From 130+ nominees, stood out for her innovation and contributions to the space industry, evaluated by a panel of esteemed judges. A star in the making! 🚀✨

1

0

4

louis030195

@louis030195

10 days

the surest path to misery is neglecting to take full ownership of your destiny

0

1

5

louis030195

@louis030195

5 months

OpenAI Assistant API is just one step closer to pure software 3.0 Programming in English only At the moment we have to rely on software 1.0 hacks to do plumbing into LLMs context and letting it interact with the client from the server

0

4

louis030195

@louis030195

6 months

rough summary of new openai abstractions basically it's software 1.0 layers on top of software 3.0 I'm eager to see someone creating an open source nextjs api to replicate this in <200 lines of code