RubberduckFMへようこそ。このポッドキャストは大学で出会った三人のホストが自分たちの興味のあるコンピュータサイエンスやプログラミングのトピックについて自由気ままに語り合うポッドキャストです。
Rubberduck FM
Claim This Podcastby rubberduckfm
17 episodes
Updated Weekly
Accepts GuestsHas SponsorsLocation 🇯🇵
Podcast Overview
RubberduckFMへようこそ。このポッドキャストは大学で出会った三人のホストが自分たちの興味のあるコンピュータサイエンスやプログラミングのトピックについて自由気ままに語り合うポッドキャストです。
Language
🇯🇵
Publishing Since
7/19/2024
1 verified contact email on file for Rubberduck FM
Pitch yourself as a guest, propose sponsorships, or reach out directly to the host.
Recent Episodes
July 4, 2025
#17: Your iPhone Doesn't Support Liquid Glass?
The hosts discuss WWDC 25, covering topics like Metal 4 for Games, Liquid Glass, Xcode 26, SwiftUI performance, AlarmKit API, WebKit for SwiftUI, and Foundation Models Framework.
May 25, 2025
#16: Codex CLI: Like a 1990s Programmer
The hosts discuss and review Codex CLI, OpenAI's open-source code agent, after examining its code, offering their impressions and insights.
April 13, 2025
#15: Princess Mononoke rages against Image Generation
<p>MasaがGPT-4o画像生成の仕組みについて、各エンジニアの予想を調査したのでそれについて話します。</p><ul> <li><a href="https://www.amazon.co.jp/Python%E3%81%A7%E5%AD%A6%E3%81%B6%E7%94%BB%E5%83%8F%E7%94%9F%E6%88%90-%E6%A9%9F%E6%A2%B0%E5%AD%A6%E7%BF%92%E5%AE%9F%E8%B7%B5%E3%82%B7%E3%83%AA%E3%83%BC%E3%82%BA-%E5%8C%97%E7%94%B0%E4%BF%8A%E8%BC%94/dp/4295021105" rel="ugc noopener noreferrer" target="_blank">Pythonで学ぶ画像生成 機械学習実践シリーズ</a></li> <li><a href="https://note.com/shunk031/n/nc1106f2ef926" rel="ugc noopener noreferrer" target="_blank">dataclass で万物に型を付けよう</a></li> <li><a href="https://www.limitless.ai/" rel="ugc noopener noreferrer" target="_blank">Limitless Pendant</a></li> <li><a href="https://www.amazon.co.jp/%E5%89%B5%E4%BD%9C%E3%81%99%E3%82%8B%E9%81%BA%E4%BC%9D%E5%AD%90-%E5%83%95%E3%81%8C%E6%84%9B%E3%81%97%E3%81%9FMEME%E3%81%9F%E3%81%A1-%E6%96%B0%E6%BD%AE%E6%96%87%E5%BA%AB-%E5%B0%8F%E5%B3%B6-%E7%A7%80%E5%A4%AB/dp/4101016410" rel="ugc noopener noreferrer" target="_blank">創作する遺伝子 僕が愛したMEMEたち</a></li> <li><a href="https://www.youtube.com/watch?v=mf4eOYUY35A" rel="ugc noopener noreferrer" target="_blank">【トーク】インパルス板倉 嫉妬した芸人ベスト10！板倉が抱えていた様々な「言い訳クリスタル」を粉砕した芸人たちを本音で話す！</a></li> <li><a href="https://wwws.warnerbros.co.jp/mickey17/index.html" rel="ugc noopener noreferrer" target="_blank">Mickey 17</a></li> <li><a href="https://ja.wikipedia.org/wiki/%E3%83%9D%E3%83%B3%E3%83%BB%E3%82%B8%E3%83%A5%E3%83%8E" rel="ugc noopener noreferrer" target="_blank">Bong Joon Ho</a></li> <li><a href="https://ja.wikipedia.org/wiki/%E3%83%AD%E3%83%90%E3%83%BC%E3%83%88%E3%83%BB%E3%83%91%E3%83%86%E3%82%A3%E3%83%B3%E3%82%BD%E3%83%B3" rel="ugc noopener noreferrer" target="_blank">Robert Pattinson</a></li> <li><a href="https://www.amazon.co.jp/%E3%83%9F%E3%83%83%E3%82%AD%E3%83%BC7-%E3%83%8F%E3%83%A4%E3%82%AB%E3%83%AF%E6%96%87%E5%BA%ABSF-%E3%82%A8%E3%83%89%E3%83%AF%E3%83%BC%E3%83%89%E3%83%BB%E3%82%A2%E3%82%B7%E3%83%A5%E3%83%88%E3%83%B3/dp/4150123950" rel="ugc noopener noreferrer" target="_blank">Mickey7</a></li> <li><a href="https://tryswift.jp/2025/#timetable" rel="ugc noopener noreferrer" target="_blank">try! Swift Tokyo Timetable</a></li> <li><a href="https://developer.apple.com/wwdc25/" rel="ugc noopener noreferrer" target="_blank">WWDC 2025</a></li> <li><a href="https://maps.apple.com/place?auid=559098170073364042" rel="ugc noopener noreferrer" target="_blank">Apple Park</a></li> <li><a href="https://www.anthropic.com/news/claude-3-7-sonnet" rel="ugc noopener noreferrer" target="_blank">Claude 3.7 Sonnet</a></li> <li><a href="https://platform.openai.com/docs/guides/realtime" rel="ugc noopener noreferrer" target="_blank">OpenAI Realtime API</a></li> <li><a href="https://tc39.es/" rel="ugc noopener noreferrer" target="_blank">TC39</a></li> <li><a href="https://seattlejs.com/" rel="ugc noopener noreferrer" target="_blank">SeattleJS</a></li> <li><a href="https://github.com/tc39/proposal-temporal" rel="ugc noopener noreferrer" target="_blank">Temporal</a></li> <li><a href="https://github.com/bloomberg/ts-blank-space/tree/main" rel="ugc noopener noreferrer" target="_blank">ts-blank-space</a></li> <li><a href="https://github.com/bloomberg/ts-blank-space/blob/main/docs/unsupported_syntax.md" rel="ugc noopener noreferrer" target="_blank">TypeScript syntax not supported by `ts-blank-space`</a></li> <li><a href="https://deno.com/blog/deno-v-oracle2" rel="ugc noopener noreferrer" target="_blank">Oracle justified its JavaScript trademark with Node.js—now it wants that ignored</a></li> <li><a href="https://ja.wikipedia.org/wiki/Sun_Microsystems" rel="ugc noopener noreferrer" target="_blank">Sun Microsystems</a></li> <li><a href="https://www.oracle.com/application-development/technologies/jet/oracle-jet.html" rel="ugc noopener noreferrer" target="_blank">Oracle JavaScript Extension Toolkit</a></li> <li><a href="https://www.imax.com/movie/princess-mononoke" rel="ugc noopener noreferrer" target="_blank">Princess Mononoke 4K IMAX</a></li> <li><a href="https://openai.com/index/introducing-4o-image-generation/" rel="ugc noopener noreferrer" target="_blank">Introducing 4o Image Generation</a></li> <li><a href="https://en.wikipedia.org/wiki/Autoregressive_model" rel="ugc noopener noreferrer" target="_blank">Autoregressive model</a></li> <li><a href="https://medium.com/@akash.kesrwani99/understanding-next-token-prediction-concept-to-code-1st-part-7054dabda347" rel="ugc noopener noreferrer" target="_blank">Understanding Next Token Prediction</a></li> <li><a href="https://openai.com/index/sora/" rel="ugc noopener noreferrer" target="_blank">Sora: Creating video from text</a></li> <li><a href="https://openai.com/index/video-generation-models-as-world-simulators/" rel="ugc noopener noreferrer" target="_blank">Video generation models as world simulators</a></li> <li><a href="https://maps.app.goo.gl/ivn1uwceBDRXkW8x7" rel="ugc noopener noreferrer" target="_blank">Bay Bridge 近くのOpenAIオフィスはありました</a></li> <li><a href="https://en.wikipedia.org/wiki/Golden_Gate_Bridge" rel="ugc noopener noreferrer" target="_blank">Golden Gate Bridge</a></li> <li><a href="https://en.wikipedia.org/wiki/San_Francisco%E2%80%93Oakland_Bay_Bridge" rel="ugc noopener noreferrer" target="_blank">San Francisco–Oakland Bay Bridge</a></li> <li><a href="https://zenn.dev/discus0434/articles/gemini-2-0-mm#gpt-4o" rel="ugc noopener noreferrer" target="_blank">1人目 動詞 さんの予想</a></li> <li><a href="https://zenn.dev/discus0434/articles/gemini-2-0-mm" rel="ugc noopener noreferrer" target="_blank">GPT-4oとGemini-2.0の画像生成能力はいかにして作られているのか</a></li> <li><a href="https://arxiv.org/abs/2206.10789" rel="ugc noopener noreferrer" target="_blank">[2206.10789] Scaling Autoregressive Models for Content-Rich Text-to-Image Generation</a></li> <li><a href="https://arxiv.org/abs/2110.04627" rel="ugc noopener noreferrer" target="_blank">[2110.04627] Vector-quantized Image Modeling with Improved VQGAN</a></li> <li><a href="https://arxiv.org/abs/2309.02591" rel="ugc noopener noreferrer" target="_blank">[2309.02591] Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning</a></li> <li><a href="https://arxiv.org/abs/2312.17172" rel="ugc noopener noreferrer" target="_blank">[2206.03605] Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action</a></li> <li><a href="https://arxiv.org/abs/2402.12226" rel="ugc noopener noreferrer" target="_blank">[2402.12226] AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling</a></li> <li><a href="https://arxiv.org/abs/2404.02905" rel="ugc noopener noreferrer" target="_blank">[2404.02905] Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction</a></li> <li><a href="https://x.com/gdb/status/1790869434174746805" rel="ugc noopener noreferrer" target="_blank">A GPT-4o generated image, 2024年5月</a></li> <li><a href="https://x.com/sang_yun_lee/status/1905411685499691416" rel="ugc noopener noreferrer" target="_blank">2人目 Sangyun Lee さんの予想</a></li> <li><a href="https://arxiv.org/abs/2310.01400" rel="ugc noopener noreferrer" target="_blank">[2310.01400] Sequential Data Generation with Groupwise Diffusion Process</a></li> <li><a href="https://x.com/nrehiew_/status/1905414817034150362?ref_src=twsrc%5Etfw%7Ctwcamp%5Etweetembed%7Ctwterm%5E1905414817034150362%7Ctwgr%5Efe84da6b6ebaa1be6695d511a55f9488aeb18d94%7Ctwcon%5Es1_&ref_url=https%3A%2F%2Fembed.zenn.studio%2Ftweetzenn-embedded__5b533073516a8" rel="ugc noopener noreferrer" target="_blank">3人目 Wh さんの予想</a></li> <li><a href="https://arxiv.org/abs/2406.11838" rel="ugc noopener noreferrer" target="_blank">[2406.11838] Autoregressive Image Generation without Vector Quantization</a></li> <li><a href="https://arxiv.org/abs/2105.01601" rel="ugc noopener noreferrer" target="_blank">[2105.01601] MLP-Mixer: An all-MLP Architecture for Vision</a></li> <li><a href="https://ja.wikipedia.org/wiki/%E6%9D%A1%E4%BB%B6%E4%BB%98%E3%81%8D%E7%A2%BA%E7%8E%87%E5%88%86%E5%B8%83" rel="ugc noopener noreferrer" target="_blank">条件付き確率分布</a></li> <li><a href="https://x.com/K_Ishi_AI/status/1905814145456607622" rel="ugc noopener noreferrer" target="_blank">4人目 K.Ishi さんの予想</a></li> <li><a href="https://arxiv.org/abs/2408.11039" rel="ugc noopener noreferrer" target="_blank">[2408.11039] Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model</a></li> <li><a href="https://x.com/sainingxie/status/1905070799901651033?ref_src=twsrc%5Etfw%7Ctwcamp%5Etweetembed%7Ctwterm%5E1905070799901651033%7Ctwgr%5Ebd6e74e2ef61fb93c0a3dc8c09aaf4c02968db44%7Ctwcon%5Es1_&ref_url=https%3A%2F%2Fembed.zenn.studio%2Ftweetzenn-embedded__38976a1b7cf8" rel="ugc noopener noreferrer" target="_blank">5人目 Saining Xie さんの予想</a></li> <li><a href="https://arxiv.org/abs/2103.00020" rel="ugc noopener noreferrer" target="_blank">[2103.00020] Learning Transferable Visual Models From Natural Language Supervision</a></li> <li><a href="https://arxiv.org/abs/2112.10752" rel="ugc noopener noreferrer" target="_blank">[2112.10752] High-Resolution Image Synthesis with Latent Diffusion Models</a></li> <li><a href="https://x.com/SaxenaNayan/status/1905334927526105492" rel="ugc noopener noreferrer" target="_blank">6人目 Nayan Saxena さんの予想</a></li> <li><a href="https://x.com/SaxenaNayan/status/1905114054076555534" rel="ugc noopener noreferrer" target="_blank">OpenAI image gen actually shows just 5 frames</a></li> <li><a href="https://arxiv.org/abs/2005.14165" rel="ugc noopener noreferrer" target="_blank">[2005.14165] Language Models are Few-Shot Learners</a></li> <li><a href="https://openai.com/index/introducing-4o-image-generation/#in-context-learning" rel="ugc noopener noreferrer" target="_blank">4o Image Generation In-Context Learning</a></li></ul>
17 total episodes available
Deep-dive analytics for Rubberduck FM
Frequently asked questions
Have a different question and can't find the answer you're looking for? Reach out to our support team by sending us an email and we'll get back to you as soon as we can.
- What is Rubberduck FM?
- How often does this podcast release new episodes?
This podcast updates weekly.
- Where can I listen to this podcast?
This podcast is available on 4 platforms including Apple Podcasts, Spotify, and more. You can also use the RSS feed directly.
- Does this podcast accept guests?
Information about guest appearances is not available.
Legal Disclaimer
Pod Engine is not affiliated with, endorsed by, or officially connected with any of the podcasts displayed on this platform. We operate independently as a podcast discovery and analytics service.
All podcast artwork, thumbnails, and content displayed on this page are the property of their respective owners and are protected by applicable copyright laws. This includes, but is not limited to, podcast cover art, episode artwork, show descriptions, episode titles, transcripts, audio snippets, and any other content originating from the podcast creators or their licensors.
We display this content under fair use principles and/or implied license for the purpose of podcast discovery, information, and commentary. We make no claim of ownership over any podcast content, artwork, or related materials shown on this platform. All trademarks, service marks, and trade names are the property of their respective owners.
While we strive to ensure all content usage is properly authorized, if you are a rights holder and believe your content is being used inappropriately or without proper authorization, please contact us immediately at hey@podengine.ai for prompt review and appropriate action, which may include content removal or proper attribution.
By accessing and using this platform, you acknowledge and agree to respect all applicable copyright laws and intellectual property rights of content owners. Any unauthorized reproduction, distribution, or commercial use of the content displayed on this platform is strictly prohibited.