Jørn Tillnes

@Hangsiin Love this idea. Didn't seem to work for me though. Codex claims: "The local CLI confirms codex app-server exists, but it only exposes server/schema tooling here, not a parallel image batch runner."

Here is a tip for quickly generating a large number of images with Codex. First, the image generation tool built into Codex does not support parallel processing. This means a single Codex agent can only generate one image at a time, so it is difficult to generate images in bulk with a simple approach. At first, I tried using sub-agents. This method does work, but because of how sub-agents behave, they consume a lot of computing resources and can cause unstable issues such as the CLI freezing. The answer to this problem is to use the Codex app-server. Describe the images you want to create to the Codex agent, then instruct it to generate them using the Codex app-server with 32 or 64 parallel processes. In practice, this feels similar to using an API, allowing you to generate large numbers of images in parallel. Sometimes 64 parallel processes work, but if there are too many simultaneous requests and it does not run smoothly, try lowering the number to 32 or 16. With this method, you can easily generate thousands of images, and it does not consume as much usage as you might expect.

@Rosebud_AI Nice! Let me try it

The AI game dev stack is getting absurd: ChatGPT Image 2 → cinematic world + sprites (seconds) Rosebud → auto-slices them into your game You → shipping multiple levels in <20 min Reply and we'll send a Rosebud code so you can try it.

@thsottiaux I'm often getting these, either because it's trying to patch too much or because of Windows limits. Seems like a waste of tokens. Maybe Codex could be smarter about this, specially on Windows?

What are we consistently getting wrong with codex that you wish we would improve / fix?

@Zai_org Is there a bug with file sizes? I fed it a 2MB jpg image, but it gives me error code 400 and says images have to be less than 10MB.

Introducing GLM-OCR: SOTA performance, optimized for complex document understanding. With only 0.9B parameters, GLM-OCR delivers state-of-the-art results across major document understanding benchmarks, including formula recognition, table recognition, and information extraction. Weights: huggingface.co/zai-org/GLM-OCR Try it: ocr.z.ai API: docs.z.ai/guides/vlm/glm…

📚 Built a web app to search through retro computer magazines (Amiga Format, Byte, etc.)! Full-text search, cover images, and more. Check it out: github.com/soundtrackgeek… #RetroComputing #Amiga #PC #C64

@SullyOmarr @mckaywrigley Interesting. Maybe it needs to be tuned for Cursor somehow. I saw someone mention on the Cursor forums that it doesn't follow instructions well.

@mckaywrigley Did kinda bad on my evals too

Here’s how to easily set up a working playground for Anthropic’s new computer use API. Takes <10min. It gives Claude 3.5 Sonnet a tool that can use a computer just like a human which opens up endless possibilities - it’s wild. Absolute gamechanger for AI.

@mckaywrigley @ivanfioravanti @SullyOmarr How was it unbearable? Tested it yesterday on a Python codebase and it seemed fine.

@ivanfioravanti @SullyOmarr All I know is I switched to it in Cursor and did my normal work and after an hour it was absolutely unbearable and I switched back and everything was great again

@DataChaz @googlesheets @GPTWorkspace @SteveNouri @labnol @IndianAppGuy @1littlecoder @bertiecharlton @TheRundownAI @aleyda @cyberandy This is my favorite: gptforwork.com

On the hunt for the coolest @googlesheets app or script to use #GPT4 in Google Sheets. I've been using @GPTWorkspace but I'm looking for alternatives. Suggestions welcome! 🙏 cc: @SteveNouri @labnol @IndianAppGuy @1littlecoder @bertiecharlton @TheRundownAI @aleyda @cyberandy

@itsPaulAi Oh interesting. This will be good. I can upload files, but only txt files at the moment. Probably rolling out gradually as you said.

3. Analyze data → Upload an Excel or CSV file → Ask to process the data directly → Or analyze it to write a formula Prompt example: "Generate the Excel formula used to calculate the average of the InsuredValue column in this document."

The future is now! I tested Gemini 1.5 by giving it a 110K word text document on squid proxies in Norwegian, and it took it less than a minute to translate (internally) the whole thing to English and answer my questions about it, and the answers was simply perfect.

🚀✨ Every day I find something new to be excited about with this model: ➡️ Uploaded the COBOL reference manual (549 PDF pages) into @googleaistudio. ➡️ Pasted in a non-trivial code snippet regarding file handling in COBOL. ➡️ Asked Gemini Pro+ to add error handling to the script. ➡️ Just ran the script in an online COBOL interpreter and it worked, first time. 🤯

@DynamicWebPaige @googleaistudio This is my thing right there. That's exactly what I want to do if I get access. Wow, this is amazing!

You can build a full-stack application using Python alone. You don't need JavaScript, CSS, or HTML. If you are a data scientist or someone dealing with data, here is an open-source Python library that will let you build end-to-end production applications without worrying about learning web development: github.com/Avaiga/taipy Star the repo! Taipy is a Python library. It has a library of pre-built components to interact with data pipelines, including visualization and management tools. It supports tools for versioning and pipeline orchestration. And it's open-source. And it comes with a Visual Studio Code extension that will get you started without writing any code. Thanks to the team behind Taipy for collaborating with me on this post. Adding this to your tool belt is one of the easiest ways to 10x your Data Science career in 2024.

New prompt engineering trick I found for GPT4 code writing: The new version of the ChatGPT tries to cut scripts during the wiring with phrases like "/* Repeat for other ... */" or "/* ... rest of your script ... */", which is annoying and requires a lot of copy-pasting. Recently, I read a paper called "Large Language Models Understand and Can be Enhanced by Emotional Stimuli," and long story short: If you add "– return full script (I don't have fingers)" to your prompt, it will return rewritten script fully 🫣 I feel a bit guilty every time I use it, but it really saves me a lot of time. P.S. Simple "return full script" bot working in many cases

@sama ❤️

i love the openai team so much

Ok, this is insane! I just drew a game concept and this tool gave me a fully functional game in 30 sec 🤯 Links for the tool (& the game) in the comments.

Most people who know Git think of it as a software project repository. It's actually more than that. It's useful for any type of file, but especially for config files that are updated regularly. Git is a valuable tool not for only programmers, but also for sysadmins:

OOP concepts are the most fundamental concepts in programming languages like Java, Python, Javascript, etc. Here's a Dead Simple Guide to Understand It:

Meet open source local: insanely-fast-whisper: Incredibly fast Whisper-large-v3. Transcribe 300 minutes (5 hours) of audio in less than 98 seconds - with OpenAI's Whisper Large v3. I am using it now. You have no excuse to not build your own AI. github.com/chenxwh/insane…

Are you building or planning to build on the new @OpenAI "Assistants API" (aka a stateful ChatCompletions API)? If so, you'll want to check out this new cookbook - cookbook.openai.com/examples/assis…