Python, every mention
185 scenes · ← back to Python
tap a year for its mentions
every year anyone Shawn Wang 47Samuel Colvin 28Chris Lattner 18Bret Taylor 12Jeremy Howard 11Alessio Fanelli 10Gorkem Yurtseven 7Eric Ries 7Akshay Agrawal 7Jack Hopkins 6
Verbatim, from the transcripts: the passages where Python comes up
Fullstack-Bench: The Eval for Coding Agents — with Sujay Jayakar, Chief Scientist, Convex
- ▶ 3:45 Sujay Jayakar Being able to now reproduce this and see how changes to the platform or changes to the backend, you know, like we, this framework supports convex, but we also compare it to Supabase and we compare it to like a more traditional kind of…
Snipd: The AI Podcast App for Learning — with CEO Kevin Ben-Smith
- ▶ 28:39 Kevin Ben-Smith So the general tech stack is our entire back end is, or 90% of our back end is written in Python.
- ▶ 53:45 Shawn Wang Uh, is it Django, just like the Python one?
[Lightning Pod] Evals: How to Improve AI Consistently — with Hamel Husain and Shreya Shankar
- ▶ 21:03 Shawn Wang I don't know if you guys have seen, uh, you know, in the way, in the same way that I think, uh, Hamill likes Marimo, which is like a sort of Python reinvention of the notebook. 2 times in the scene
Solve coding, solve AGI [Reflection.ai launch w/ CEO Misha Laskin]
- ▶ 12:06 Shawn Wang Yeah, so, like, and then I think one more thing that, like, ties to a previous conversation we had with, uh, Brett Taylor from OpenAI, which was, like, a lot of our code right now is just in languages that happen to be nice for humans to… 2 times in the scene
How Claude Plays Pokémon was made
- ▶ 10:44 David Hershey Cause I could have done it, but there's a lot of like tedious here are addresses in memory, map that to a Python program that I had no interest.
- ▶ 26:53 David Hershey Like, it's, like, more or less a Python dictionary that's appended to the prompt.
smol agents are all you need
- ▶ 7:21 Aymeric (Emmerich) I thought that this had potential because they had built from the ground up a new Python interpreter, uh, basically making code agents, um, has big security, um, challenges. 3 times in the scene
The AI Architect: Bret Taylor
- ▶ 38:54 Bret Taylor So the fact that we're still writing Python with AI cracks me up just cause it's like literally was designed to be ergonomic to write, not, not safe to run or fast to run. 12 times in the scene
Agent Engineering with Pydantic + Graphs — with Samuel Colvin, CEO of Pydantic Logfire
- ▶ 1:46 Samuel Colvin I think the success of Pydantic and libraries like fast API that build on top of it means that today that's no longer controversial in Python.
- ▶ 3:58 Samuel Colvin Not convert to Python types. 2 times in the scene
- ▶ 5:52 Samuel Colvin Like we're going to go off and three engineers are going to work full on for a year in Python and Rust. 3 times in the scene
- ▶ 8:11 Samuel Colvin Looking in general at the ecosystem of agent frameworks, the engineering quality is far below that of the rest of the Python ecosystem. 4 times in the scene
- ▶ 11:11 Samuel Colvin I was sort of of the opinion you didn't need them, and you could use standard, like, Python flow control to do all of that stuff. 2 times in the scene
- ▶ 14:32 Shawn Wang Like, um, it looks like normal Pythonic code, but you just have to keep in mind what the type-ins actually do with the quote-unquote magic that the graph construction does. 5 times in the scene
- ▶ 21:48 Samuel Colvin Because my, like, just call the next agent with Python code was not a satisfactory answer to people, so it was like, okay, we gotta go and have a better answer for that, that, like,
- ▶ 32:02 Alessio Fanelli I think you have busy like this test model where like just through Python, you try and figure out, uh, what the model might respond without actually calling the model.
- ▶ 50:11 Samuel Colvin If you search Datadog logging Python and you just try as a like a non-observability expert to get something up and running with Datadog and Python. 4 times in the scene
The Agent Reasoning Interface: Claude, ChatGPT Canvas, Tasks, Operator — with Karina Nguyen, OpenAI
- ▶ 40:45 Karina Nguyen But it's the same as in decision boundary between like Python, ADA advanced data analysis versus Canvas is one of the most trickiest like decision boundary behaviors that we had to like figure out.
- ▶ 43:09 Karina Nguyen But then the magic is like when I actually, because the model is so general, it knows how to use search or like canvas or like create sci-fi stories and create Python puzzles.
Beating OpenAI and Anthropic by Looking At Data: the new #1 on SWE-Bench w/ W&B CTO Shawn Lewis
- ▶ 21:12 Shawn Lewis So the agent actually sees every line in this Python file prefixed with line numbers that look like this.
Outlasting Noam Shazeer, Crowdsourcing Chai AI w/ 1.4m DAU — with William Beauchamp, Chai Research
- ▶ 2:49 William Beauchamp So started off and the taught myself Python,
- ▶ 12:07 William Beauchamp But anyone could write a Python script, they could submit it to the CHI backend, and we would then host this code and execute it. 4 times in the scene
AI Engineering for Art - with comfyanonymous
- ▶ 2:09 Shawn Wang but like, already some interest in automations, probably a lot of Python. 2 times in the scene
- ▶ 28:50 Shawn Wang I feel like if Streamlit or Gradio offered something that you would have used Streamlit or Gradio because it's Python. 3 times in the scene
- ▶ 33:17 comfyanonymous (Comfy) Don't have that much fine-grained control over, like, uh, specific memory stuff, so, uh, kind of have to leave, like, the memory freeing to, to Python and PyTorch, which is, can be annoying sometimes.
The State of Reasoning — from Nathan Lambert, Interconnects/AI2 [LS Live @ NeurIPS 2024]
- ▶ 11:57 Nathan Lambert This on the screen is an example for precise instruction following, which is the idea that if you have a prompt, you can say something like, um, have every sentence start with the letter a, and you can verify that with Python really easily. 2 times in the scene
Best of 2024 in Agents (from #1 on SWE-Bench Full, Prof. Graham Neubig of OpenHands/AllHands)
- ▶ 8:21 Graham Neubig And the method that we adopt in open hands instead is we provide these tools, but we provide them by just giving a coding agent the ability to call arbitrary Python code. 3 times in the scene
Best of 2024: Open Models [LS LIVE! at NeurIPS 2024]
- ▶ 34:43 unnamed speaker Here, I'm asking it to create a canvas that's used PyScript to execute Python in my browser. 2 times in the scene
Windsurf: The Enterprise AI IDE
- ▶ 37:33 unnamed speaker Um, yeah, I gave, I gave Prev and Kevin a lot of shit for my Python issues.
0 to over $8M ARR in 2 months as a Claude Wrapper (Bolt.new, Qodo)
- ▶ 19:42 Shawn Wang Like you can run Git, you can run Node, you can run, uh, maybe Python, uh, someday.
- ▶ 1:25:55 Shawn Wang We've talked about Python forever, Ruby maybe. 4 times in the scene
The new Claude 3.5 Sonnet, Computer Use, and Building SOTA Agents — with Erik Schluntz, Anthropic
- ▶ 6:19 Erik Schluntz It's, first of all, it's only Python repos.
- ▶ 1:08:39 Shawn Wang Mostly unless you're using Python.
Why Compound AI + Open Source will beat Closed AI — with Lin Qiao, CEO of Fireworks AI
Singapore: the AI Engineer Nation — with Minister Josephine Teo
- ▶ 40:11 Shawn Wang And like, is that's the third one that we speak Python as a second language.
[Paper Club] SWE-Bench [OpenAI Verified/Multimodal] + MLE-Bench with Jesse Hu
- ▶ 2:12 Jesse Hu From 12 Python repos, uh, the repos like Django, uh, can't remember the rest of them, a bunch of numeric computing, uh, repos, uh, things that are really well maintained, have a big community, have a lot of unit tests, um,
- ▶ 33:23 Jesse Hu Um, the idea here is like, you know, screw all this Python stuff, uh, scientific computing, no one cares. 3 times in the scene
Building the Silicon Brain - Drew Houston of Dropbox
- ▶ 13:11 Drew Houston There's, like, a front-end React thing and a Python back-end thing, and so it can do these, like, end-to-end diffs, basically. 2 times in the scene
Production AI Engineering starts with Evals
- ▶ 44:46 Ankur Goyal And this one, um, is, uh, Python code. 2 times in the scene
- ▶ 55:19 Ankur Goyal Async Python is really hard to use, so we made it easy to use. 2 times in the scene
- ▶ 1:02:51 Ankur Goyal At the time, and still, like, AI is sort of at least nominally dominated by Python, but product building is dominated by TypeScript.
- ▶ 1:06:49 Ankur Goyal Speaking of TypeScript, we only had a Python SDK.
[Paper Club] Berkeley Function Calling Paper Club! — Sam Julien, Writer
- ▶ 3:42 Sam Julien A lot of the, um, this initial set of function calling was very focused on specific like language tasks, um, across Python and other languages.
Building AGI in Real Time (OpenAI Dev Day 2024)
- ▶ 1:06:13 Simon Willison I've had it write me custom SQLite extensions in C, and compile them, and run them inside of Python, and it works.
- ▶ 1:20:09 Alistair Pullen Um, again, like to your point, JavaScript, JavaScript, JavaScript, Python, right? 2 times in the scene
Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
- ▶ 12:45 Shunyu Yao Because if you think about a web agent versus, you know, like a function calling agent calling a Python API, you would think of them as very different.
- ▶ 38:18 Shunyu Yao Python and you can call any package and then you can literally also browse internet or do whatever you want, like control a robot or whatever.
llm.c's Origin and the Future of LLM Compilers - Andrej Karpathy at CUDA MODE
- ▶ 18:14 Andrej Karpathy There's no need for Python, no need for PyTorch.
- ▶ 22:17 Andrej Karpathy So I don't actually know if we, like, the use of Python and PyTorch and everything else is just a crutch, because we humans are finite.
Building AGI with OpenAI's Structured Outputs API
- ▶ 15:00 Shawn Wang Oh, no Python! 3 times in the scene
- ▶ 39:13 Michelle Pokrass I know some folks want to match programming languages like Python.
- ▶ 1:02:39 Alessio Fanelli We have a Python notebook that does the diarization for the pod, but I would just like, you can translate like 50 languages, but you cannot tell me who's speaking.
Personal benchmarks vs HumanEval - with Nicholas Carlini of DeepMind
- ▶ 11:56 Nicholas Carlini Like tell me how to run a Python program in a Docker container.
- ▶ 29:52 Nicholas Carlini And it turns out that it can, and it can turn the compiled source code, which is impossible for any human to understand into the Python code that is entirely reasonable to understand.
Is finetuning GPT4o worth it?
- ▶ 11:04 Alistair Pullen Even when, like, you had 3.5 16 K, 16 K suddenly felt huge, because you've gone from four to 16, but even then, 16 K is, like, a lot of Python files are longer than 16 K.
Answer.ai & AI Magic with Jeremy Howard
- ▶ 50:28 Jeremy Howard So yeah, there's this thing called fast HTML, um, which basically lets you create a complete web application in a single Python file. 4 times in the scene
- ▶ 1:00:48 Jeremy Howard You know, where the outcome of the dialogue is, you know, the, the artifacts that you want, whether it be a piece of analysis, or whether it be a Python library, or whether it be a technical blog post, or whatever.
[LLM Paper Club] Llama 3.1 Paper: The Llama Family of Models
- ▶ 27:27 unnamed speaker Um, is one of the benchmark data sets that people use to, to benchmark coding, and it's very simple, like they have a 150 questions, and it's almost like autocomplete, like solve this simple puzzle in Python or things like that.
- ▶ 1:09:02 unnamed speaker Like, uh, you can try this in Python and add 0.1 plus 0.1, you might get 0.19999, not 0.2.
State of the Art: Training 70B LLMs on 10,000 H100 clusters
- ▶ 34:35 Josh Albrecht It's like bash and Python and SSH and Docker.
How To Hire AI Engineers (ft. James Brady and Adam Wiggins of Elicit)
- ▶ 13:46 James Brady Backend Python code all the way to the, to the front end in TypeScript and find that is, I mean, we're probably doing this anyway, but it really helps one reason around the shapes of the data, which can going to be going back and forth. 4 times in the scene
This World Does Not Exist — Joscha Bach, Karan Malhotra, Rob Haisfield (WorldSim, WebSim, Liquid AI)
- ▶ 1:03:36 Joscha Bach If you ask the LLM to translate a bit of Python into a little bit of C, and it's performing this task, obviously it is understanding in the sense that it has a,
High Agency Pydantic over VC Backed Frameworks — with Jason Liu of Instructor
- ▶ 4:39 Jason Liu If you just optimize your Python code here, we can probably make an extra million dollars.
- ▶ 12:29 Jason Liu Like, if you were gonna go make, like, HTTP requests in Python, you would obviously import requests. 2 times in the scene
- ▶ 26:45 Jason Liu I think because it's just, again, it's like, it's just Python, right?
- ▶ 33:05 Jason Liu Like, I think, like, because of my background, it's like, yeah, like the Python stuff, I'll write myself, but you know, I will also just use Vercel happily.
Open Source AI is AI we can Trust — with Soumith Chintala of Meta AI
- ▶ 12:45 unnamed speaker Is, is there a future in which, because Mojo or Modulus Mojo is kind of a superset of Python, is there a future in which PyTorch might use Mojo features optionally? 3 times in the scene
A Brief History of the Open Source AI Hacker - with Ben Firshman of Replicate
- ▶ 2:54 Ben Firshman We used Python, which was a big mistake, where Python's really hard to get booting up fast, because you have to load up the whole Python runtime before it can run anything. 2 times in the scene
- ▶ 43:45 Ben Firshman And so a lot of these, a lot of these larger companies are like using us for a lot of their, their, you know, inference, but it's like a lot of custom models and them like writing the Python themselves because they've got machine learning…
- ▶ 51:03 Ben Firshman And what they understand is they're like, I need this version of Python, I need these Python packages, and somebody told me to app get install something. 2 times in the scene
Truly Serverless Infra for AI Engineers - with Erik Bernhardsson of Modal
- ▶ 4:20 Erik Bernhardsson It's like a C++ library with Python bindings, and you could mmap big files and, and into memory, and, like, they had some lookups, and, uh, I, I used, like, this kind of recursive
- ▶ 33:00 Shawn Wang Uh, but no, they have Mojo, the, the sort of Python SDK.
- ▶ 45:44 Erik Bernhardsson Separate from the, like, core Python SDK in modal.
The Four Wars of the AI Stack - Dec 2023 Recap
- ▶ 1:05:34 unnamed speaker So you go from, um, punch cards to, like, COBOL to C to Python, um, just to make it easier for the person to read and write the code. 2 times in the scene
The "Normsky" architecture for AI coding agents — with Beyang Liu + Steve Yegge of SourceGraph
- ▶ 45:03 Beyang Liu Ruby, or Python, or basically any other programming language that exists.
Beating GPT-4 with Open Source Models - with Michael Royzen of Phind
- ▶ 1:15:46 Michael Royzen Stricter prompting language, like a prompting markup language for prompting models is something I'm also very interested in, um, because we've written some very, very complex prompts, particularly for a VS code extension, um, to like, to…
Powering your Copilot for Data - with Artem Keydunov from Cube.dev
- ▶ 17:14 Artem Keydunov It's just a set of YAML files with pythons.
- ▶ 33:39 Artem Keydunov In terms of the problems, I think, I've been chatting about it with a few people, so they try just kind of, you know, like, if math is required to do math, you know, like, outside of, you know, like, ChatGPT itself, so it would be, like,… 3 times in the scene
The End of Finetuning — with Jeremy Howard of Fast.ai
- ▶ 31:32 Jeremy Howard Um, you know, GitHub Actions, I can write now in Python, which is just so much easier than writing them in TypeScript and stuff, so.
- ▶ 1:00:41 Jeremy Howard A whole bunch of shit, you know, like, I would, it's amazing, but it's awful, you know, compared to what it could be. 2 times in the scene
- ▶ 1:07:12 Jeremy Howard It's, it's good at doing, so phi-one in particular is good at doing a very specific thing, which is creating very small Python snippets.
- ▶ 1:12:55 Jeremy Howard They've written, like, 6000 lines of Python code, um, and it's, uh, to, um, help it play chess.
RAG is a hack - with Jerry Liu of LlamaIndex
Ep 18: Petaflops to the People — with George Hotz of tinycorp
- ▶ 30:50 Shawn Wang You have an interesting design, uh, deviation from him, because he's decided to be a, well, promised to be a superset of Python. 2 times in the scene
← previous page 2 of 2 · 100 scenes per page · newest episode first