AI/ML News & Innovations Hub

`openai_ex`: elixir client with latest APIs

openai_ex 0.9.22 is out. Responses gains server-side compaction, cancel for background responses, and input_tokens . Vector stores gain search . We now support moderation , prompt_cache_options and safety_identifier , plus other params across several endpoints. The user guide’s image sections are rewritten for the GPT image models, now that dall-e-2 is retired. Shoutout to Github user @iujames for the PR that sparked the cleanup ( Add context_management to Responses API fields by iujames · Pull Request #146 · cyberchitta/openai_ex · GitHub ). A collab with claude-opus-5, who did a lot of the heavy lifting.

GPT-Image - General AI Gallery: A Place for Images with AI created by Users

Sci-fi Industrial Site Another Sci-fi Industrial Site

Can an engineer reset my stuck DALL-E queue?

Hello, I am experiencing a persistent, server-side bug on my account that has made ChatGPT completely unusable since August 2nd. The Problem: Every single time I open a new conversation, the system automatically triggers an unwanted, non-requested image generation process. The process stays permanently “stuck” (hanging) and never finishes. Additionally, the rendering engine continuously displays a broken > character in the UI. Steps already taken: The issue persists across all platforms (Web Browser, iOS, and Android Apps) and different devices. I have already cleared the cache, reinstalled the apps, and performed every standard troubleshooting step. Standard support keeps automatically closing my tickets as “duplicates” without providing any solution. Since this happens on all devices, it is clearly a corrupted session state or a stuck queue in my account database on the server side. I need an engineer or a senior technician to manually reset my account’s active session state ( clear stuck DALL-E queue ). Please do not close my account or this thread. I am a paying user and just want this technical loop fixed. Thank you.

Moonlight & Mayhem (Raccoon Heist by Codex + GPT-5.6 Sol Ultra)

Moonlight & Mayhem (Raccoon Heist by Codex + GPT-5.6 Sol Ultra) On Wednesday I wrote about One-shotting a Raccoon Heist game using Claude Fable 5 , where I had Claude Fable 5 build a full working game from a premise I generated with GPT-3 and DALL-E four years ago . I decided to pose the exact same prompt to Codex Desktop running GPT-5.6 Sol Ultra - the mode where Sol makes aggressive use of sub-agents - to see how it would do. It produced a much better game! Here's Moonlight & Mayhem - GitHub repository here , including the textures and prompts it generated using gpt-image-2 . Your browser does not support HTML5 video. The original GPT-3 generated game description included: In “Raccoon Heist”, you and your team of thieving raccoons are tasked with pulling off a series of daring heists. From robbing banks to stealing priceless art, no job is too big or too small for your furry crew. Fable's version had you as a single raccoon running around a back yard collecting coins and fish. GPT-5.6 Sol has you in a museum, rescuing your two other raccoon crewmates in order to stack on top of each other and bust the golden sardine out of its case. Much more heisty! There was one catch though: the version produced from the one-shot prompt had a bug where each raccoon had an eyeball that was enlarged to the size of a giant sphere floating over their head! You can play that version here . Despite reviewing screenshots during development Codex failed to spot and correct this bug. I fixed it…

One-shotting a Raccoon Heist game using Claude Fable 5

Back in 2022 I tweeted screenshots of a game concept generated by GPT-3 and some concept "art" created using DALL-E. Today, on the fourth anniversary of that tweet, I decided to see if Claude Fable 5 (running in Claude Code for web ) could build the entire game from the content of that tweet. It did a pretty good job of it! You can play the game here . Here's the GitHub repo , and a short video demo: Your browser does not support HTML5 video. How I built this This is the August 5th, 2022 tweet : My GPT-3 prompt back then was: Write a detailed product description of a computer game where a team of raccoons go on heists. This was in the text completion days, where you asked GPT-3 to complete the rest of the text. It completed: In "Raccoon Heist", you and your team of thieving raccoons are tasked with pulling off a series of daring heists. From robbing banks to stealing priceless art, no job is too big or too small for your furry crew. You'll need to use your wits and your skills to avoid the police and make a clean getaway with the loot. With exciting gameplay and a charming cast of characters, "Raccoon Heist" is the perfect game for anyone looking for a light-hearted caper. My prompt to DALL-E was short: Screenshot from a video game where a team of raccoons go on a heist Today's experiment: can I dump those screenshots into Fable 5 with a prompt telling it to write a game, then leave it to its own devices and get a working game at the end? Setting Claude Code for web up to us…

From prototype to soft launch: building a deterministic AI-startup idle game with Codex

Thanks, Paul! The first working prototype came together about two weeks ago. I initially just wanted to see whether I could build a whole game with 5.6 Sol. The basic clicker loop was quick; most of the work went into balancing the nonlinear progression, offline and server-validated saves, payments, telemetry, audio, security, and iterating on feedback from friends and family. Along the way, it became a repository of jokes and reflections on AI, delivered as you progress through the game. It isn’t “done,” but then things rarely are. I wanted to put it out there, meet other people making games, and find out who might enjoy the humour.

GPT-Image - General AI Gallery: A Place for Images with AI created by Users

Here’s where those random words start to need organization. >>> list = "notorious swallow the hospital horizon of An echolalia Serendipity machine in\ a velvet feather village".split(" ") >>> " ".join(sorted(list)) 'An Serendipity a echolalia feather horizon hospital in machine notorious of swallow the velvet village'

Requesting one text element without additional text

The approach from @phyde1001 and @mitchell_d00 is pretty much what I am doing right now. Add 1, in words ‘one’, sign only. It reads… Because I don’t want to explain this to the prompt generating model in specific detail. Asking myself if there may be a better term for this, it could be: Single-element typography / one discrete typographic element

July 2026 (Theme: Perspective) — ChatGPT / API Image Generative Art Gallery, Prompt Tips, and Help

Comment on Google’s Imagen Text-to-Image Diffusion Model With Deep Language Understanding Defeats DALL-E 2 by Reeenaaaa

good one , noted in my notepad of the day

Comment on OpenAI Releases GLIDE: A Scaled-Down Text-to-Image Model That Rivals DALL-E Performance by Renna

Hi I read out this article but , comparsion between GLIDE and DALLE is good enough

July 2026 (Theme: Perspective) — ChatGPT / API Image Generative Art Gallery, Prompt Tips, and Help

DysTopia: Partially, it also depends on who is tagging along. Sometimes it’s educated bias from parent to son that also plays a key role. Partially, yes. Every child is influenced by the people and systems around them. My son is no exception. But the perspective he has inherited did not arise in a vacuum. My children have grown up with the ever-present possibility of being separated from one parent or the other by a distance they cannot meaningfully traverse. They live in a world seemingly unable to account either for their family or for the environment in which they will grow up, while remaining exceptionally good at accounting for institutions, borders and material wealth. Their right to a family life depends upon our ability to hold our communities—and the systems they sustain—to account. My son grew up in China until he was seven, where he learned fluent Chinese from the community around him and fluent English from me. We returned to the UK after the systems governing my ability to work in China changed. The move had been planned a year before COVID. Back in the UK, there were no accessible language schools capable of continuing what our children had begun, and little recognition of their parents’ work across two systems that did not properly recognise one another. The responsibility for maintaining their language, education and integration therefore fell largely to me. I had already developed reasons to distrust the West before I was thirteen. I saw systems that claimed…

July 2026 (Theme: Perspective) — ChatGPT / API Image Generative Art Gallery, Prompt Tips, and Help

Completely manufactured figures, on-demand + prompt repetition of instructions in absence of something original to say Although in 2026, as the type of person that would participate in a forum thread like this, have you taken more pictures with a camera, or made more AI pictures?

July 2026 (Theme: Perspective) — ChatGPT / API Image Generative Art Gallery, Prompt Tips, and Help

Mating Dance Prompt (click for more details) From my side porch, just saw two hawks doin the dance…

Complete and Ongoing History of the OpenAI Developer Community

I recall we had the pleasure of having @gwern here for a bit. I followed him back when he was mucking around with poetry on gpt-2. Well, I obsessively read everything coming out about LLMs back then. I suggested Gwern try some of e.e. cummings more creative works… gwern.net "r-p-o-p-h-e-s-s-a-g-r" E. E. Cummings - 1894–1962 r-p-o-p-h-e-s-s-a-g-r who...... And so I have created something more than a poetry-writing AI program. I have created a voice for the unknown human who hides within the binary. I have created a writer, a sculptor, an artist. And this writer will be able to create worlds, to give... He did a lot of cool tests with LLM poetry generation. gwern.net ‘GPT poetry’ directory Bibliography for directory 𝚊𝚒/𝚗𝚗/𝚝𝚛𝚊𝚗𝚜𝚏𝚘𝚛𝚖𝚎𝚛/𝚐𝚙𝚝/𝚙𝚘𝚎𝚝𝚛𝚢, most recent first: 1 related tag, 32 annotations, & 19 links (parent). I wonder if tagging these random cool people from the past will get them to come back… or just annoy them. Hopefully not the latter! Seriously, though, there’s some surprising names on our million user roster!

Multimodality and Large Multimodal Models (LMMs)

For a long time, each ML model operated in one data mode – text (translation, language modeling), image (object detection, image classification), or audio (speech recognition). However, natural intelligence is not limited to just a single modality. Humans can read, talk, and see. We listen to music to relax and watch out for strange noises to detect danger. Being able to work with multimodal data is essential for us or any AI to operate in the real world. OpenAI noted in their GPT-4V system card that “ incorporating additional modalities (such as image inputs) into LLMs is viewed by some as a key frontier in AI research and development .” Incorporating additional modalities to LLMs (Large Language Models) creates LMMs (Large Multimodal Models). Not all multimodal systems are LMMs. For example, text-to-image models like Midjourney, Stable Diffusion, and Dall-E are multimodal but don’t have a language model component. Multimodal can mean one or more of the following: Input and output are of different modalities (e.g. text-to-image, image-to-text) Inputs are multimodal (e.g. a system that can process both text and images) Outputs are multimodal (e.g. a system that can generate both text and images) This post covers multimodal systems in general, including LMMs. It consists of 3 parts. Part 1 covers the context for multimodality, including why multimodal, different data modalities, and types of multimodal tasks. Part 2 discusses the fundamentals of a multimodal system, using the…

Remaking Old Computer Graphics With AI Image Generation

Can AI Image generation tools make re-imagined, higher-resolution versions of old video game graphics? Over the last few days, I used AI image generation to reproduce one of my childhood nightmares. I wrestled with Stable Diffusion, Dall-E and Midjourney to see how these commercial AI generation tools can help retell an old visual story - the intro cinematic to an old video game (Nemesis 2 on the MSX). This post describes the process and my experience in using these models/services to retell a story in higher fidelity graphics. Meet Dr. Venom This fine-looking gentleman is the villain in a video game. Dr. Venom appears in the intro cinematic of Nemesis 2, a 1987 video game. This image, in particular, comes at a dramatic reveal in the cinematic. Let’s update these graphics with visual generative AI tools and see how they compare and where each succeeds and fails. Remaking Old Computer graphics with AI Image Generation Here’s a side-by-side look at the panels from the original cinematic (left column) and the final ones generated by the AI tools (right column): This figure does not show the final Dr. Venom graphic because I want you to witness it as I had, in the proper context and alongside the appropriate music. You can watch that here: