{"content_list": [{"text": "# New Updates to ChatGPT and Codex\n\n- One super app for both chatGPT and Codex\n- You can create automations from chat itself\n\nhttps://x.com/OpenAI/status/2075274271845404744?s=20\n\nIt\u2019s codex but it\u2019s re-introduced for non-coders to start work from ChatGPT work desktop!\r\n\r\n\r\nOpenAI chatGPT Twitter account also shared a look and feel, a dip toes in the water sort of dem video.\nhttps://x.com/ChatGPTapp/status/2075336584451539353?s=20\r\n\r\n\r\nWhile my work is intact on the Codex app, the icon itself has changed a bit, as in the name has changed to chatGPT instead. \n\nThe icon on the status bar, however, is still the chatGPT icon and not the Codex icon. I'm not sure if this is a bug but when I enforced custom icons to be the same as Codex itself, it didn't change on the status bar. \n\ufffc\r\n\r\n\r\n\u2026and then I opened the app and noticed 3 new models available for use:\n\n- GPT 5.6 Sol\n- GPT 5.6 Terra\n- GPT 5.6 Luna\n at this point I just don't know what they are but I want to find out quickly. \r\n\r\n\r\nMost of the marketing content on my Twitter timeline doesn't talk about soul, luna, or terror. It just talks about GPT 5.6 so clearly you might have to do things and figure out by yourselves. \n\nWhat if I asked ChatGPT itself? \r\n\r\n\r\nChatGPT also stated or cited the blog post from openAI. \n\n> We\u2019re launching the GPT\u20115.6 family of models for general availability following our limited preview\u2060: our new flagship, Sol, alongside Terra, a balanced model for everyday work, and Luna, our most cost-efficient model.\n\n> GPT\u20115.6 Sol sets a new high of 53.6, eclipsing Claude Fable 5 (adaptive reasoning) by 13.1 points. Even at medium reasoning, it beats Fable 5 by 11.4 points at roughly one-quarter the estimated cost. \n\nResults of a certain few benchmarks have been shared in this blog post.  https://openai.com/index/gpt-5-6/\r\n\r\n\r\n---\n\nFor my automations that are setup, I asked chatGPT to compare the prices of GPT 4o mini and GPT 5.6 Luna and it looks like luna is 6.7x more expensive than the former.\u2028\n> If you meant GPT\u20114o mini, the gap is larger:\n> * GPT\u20114o mini: $0.15 input / $0.60 output\n> * Luna: $1 input / $6 output\n> * Luna is approximately 6.7\u00d7 more expensive on input and 10\u00d7 on output. GPT\u20114o mini pricing\n\n---\n\nChatGPT iOS app has replaced codex tab with remote tab\r\n\r\n\r\n---\n\nThe slider feature for reasoning levels for the GPT 5.6 Sol is sort of interesting. Is this feature here to stay?\r\n\r\n\r\n---\nIt's also interesting that in the chatGPT app, without the remote connections, GPT 5.6 Terra and Luna aren't available and only Sol is. \r\n\r\n\r\n---\nAnother update then I noticed is that there are more options for selected text on the on the ChatGPT Codex app on the desktop.\u2028\u2028\n\nMore details seems to be slightly similar to \u2018Ask in Side Chat\u2019 (I think the naming wasn\u2019t changed to Side Task or whatever)?\n\nI asked GPT 5.6 Sol about this and learned the following:\n\n1. The ask \u2018for more details\u2019 basically means explain this sentence or thing in more words without worrying about follow up questions (you still can if you want to)\n2. The \u2018ask in side chat\u2019 is a more generic one where you can take things (out of context?) and ask another agent to do something with it.\u2028\u2028\nSo basically ask for more details is a more specific implementation of side-chat.\r\n\r\n\r\n---\nThere should be an /action in a /sidechat that essentially tells codex to update findings in the main thread\n", "title": "OpenAI's releases GPT 5.6 (and other changes)", "slug": "openais-releases-gpt-56-and-other-changes", "description": null, "updated_at": "2026-07-10T10:36:13.114Z", "media": ["https://cpx.tnvmadhav.me/content/image/content-images/ChatGPT.png", "https://cpx.tnvmadhav.me/content/image/content-images/NiceShotPro_-_for_mac.png", "https://cpx.tnvmadhav.me/content/image/content-images/15.6_So..png", "https://cpx.tnvmadhav.me/content/image/content-images/image_tQjHOeq.png", "https://cpx.tnvmadhav.me/content/image/content-images/Open_Codex.png", "https://cpx.tnvmadhav.me/content/image/content-images/Advanced__LIPIlJr.png", "https://cpx.tnvmadhav.me/content/image/content-images/OPT_S.6_Sol.png", "https://cpx.tnvmadhav.me/content/image/content-images/image_8xJe68W.png", "https://cpx.tnvmadhav.me/content/image/content-images/update_the_main_thread_with_these_findings_now.png"]}, {"text": "The more I work with A.I. for engineering , the more I got back to fundamental principles of a good system.\r\n\r\nNow is the best time to celebrate past efforts to get cleaner architecture.\r\n\r\nLLMs are truly autocomplete engines.\r\n\r\nClean architecture yields clean architecture.\r\n\r\nClean architecture helps human in loop comprehend autocompleted changes easily.\r\n\r\nThus resulting in faster deployment cycles.\r\n\r\nClean architecture won\u2019t matter if there are no humans in the loop.\r\n\r\nBut, if automated agents of all kinds are the workers of the future, clean architecture helps here as well.\r\n\r\nIt\u2019s a win-win strategy.\r\n\r\nLong term benefits outweigh the initial learning curves.\r\n\r\nThings can easily go wrong at the start with all the psychosis at first.\r\n\r\nFirm hand to get things put into place is a necessity.", "title": "Thoughts on A.I. for engineering", "slug": "thoughts-on-ai-for-engineering", "description": null, "updated_at": "2026-07-08T09:17:18.852Z", "media": []}, {"text": "> This is correct, I think a number of people on the tl didn\u2019t read past the title and made inferences and comparisons that are just wrong and then use it as an opportunity to take cheap shots. This is not a \u201cfeature\u201d like some crappy Slack bot and it\u2019s certainly not a Claw, though it has aspects of it. It is an org-level harness. The difference will become clearer over time.\n\nThe idea of Org Level Harness is the key subject that caught my eye.\n\nClaude Code was a butterfly effect.\r\n\r\n\r\ni'm referencing a post that can be found here: https://x.com/karpathy/status/2069822834160124091?s=12", "title": "Quoting Karpathy on @Claude slack harness ", "slug": "quoting-karpathy-on-claude-slack-harness", "description": null, "updated_at": "2026-06-25T06:17:26.861Z", "media": []}, {"text": "> The best mobile software does not shrink a desktop interface. It identifies the decisions that matter when you are away from the desk and makes those decisions fast, legible, and safe.\n\nOptionality of convenience makes your software workflows anti-fragile\n\ni'm referencing a post that can be found here: https://developers.openai.com/blog/mastering-codex-remote-for-engineering", "title": "Good read posted by OpenAI Codex iOS dev", "slug": "good-read-posted-by-openai-codex-ios-dev", "description": null, "updated_at": "2026-06-23T18:08:52.417Z", "media": []}, {"text": "> The hardest part of any task is overcoming the activation energy. The rest is just riding the momentum.\n\nBeen thinking about this too https://x.com/tnvmadhav/status/1760205214555291714?s=46\r\n\r\n\r\ni'm referencing a post that can be found here: https://x.com/fchollet/status/2068771319341367390?s=12", "title": "Quoting Chollet on achieving things", "slug": "quoting-chollet-on-achieving-things", "description": null, "updated_at": "2026-06-22T05:03:33.931Z", "media": []}, {"text": ">  it\u2019s June 2026. Stop hand editing your prompts. Hold down the dictation button and ramble for 10 minutes. Give the model every fragment, caveat, example, and vibe in your head. It is literally a large language model. If it\u2019s superhuman at anything, it\u2019s reconstructing latent intent from language.\n\nI agree with this, i have been using codex\u2019s dictation to paste my ramblings and it\u2019s decent enough for small tasks that I give it.\n\ni'm referencing a post that can be found here: https://x.com/guinnesschen/status/2068744472528314811?s=12", "title": "Quoting a post by Guinnesschen", "slug": "quoting-a-post-by-guinnesschen", "description": null, "updated_at": "2026-06-22T04:58:00.436Z", "media": []}, {"text": "In the age of A.I. based lightning fast execution, being good at finding problems just by thinking about it is a sought out skill.\n\nIdea guys with agency are surfing Shai-Hulud at this point.", "title": "This skill is worth a lot in 2026", "slug": "this-skill-is-worth-a-lot-in-2026", "description": null, "updated_at": "2026-06-21T12:29:50.484Z", "media": []}, {"text": "I completed [Dune: Prophecy](https://www.imdb.com/title/tt10466872/) last night.\n\nAn important disclaimer is that I have been a naive fan of Dune and Dune Part 2 (coming in just from my appreciation of Dennis Villeneuve), which means I haven't read Frank Herbert's books.\n\nI must say Dune:Prophecy hadn't succeeded in keeping me interested at first, however it's probably not a debate when I say the production quality is top notch.\n\nNeedless to say, I do feel it's a good one. I am captivated by the lore of this story (especially when it comes to Shai-Hulud).\r\n\r\n\r\nAlso, Thinking Machines?\n\nThat's the name of [Mira Murati's A.I. company](https://thinkingmachines.ai). \n\nNot sure if that was the inspiration but it loved the acknowledgement.\n\nIt's strange that I didn't come across this nod/acknowledgement on my twitter timeline.\r\n\r\n\r\nI liked the cameo(ish) from Mark Addy. I just love the way he speaks.\n", "title": "I watched Dune: Prophecy last night", "slug": "i-watched-dune-prophecy-last-night", "description": null, "updated_at": "2026-06-21T12:06:03.177Z", "media": []}, {"text": "Good read!\n\nhttps://simonwillison.net/2026/May/6/vibe-coding-and-agentic-engineering/", "title": "Stumbled upon a post from simon willison", "slug": "stumbled-upon-a-post-from-simon-willison", "description": null, "updated_at": "2026-05-19T04:27:47.089Z", "media": []}, {"text": "Shiny things can cause blinding to your eyes...and maybe they should.\n\nAllegory much https://boringtechnology.club/", "title": "I read a post on boring technology", "slug": "i-read-a-post-on-boring-technology", "description": null, "updated_at": "2026-05-13T09:58:30.145Z", "media": []}], "user": {"username": "tnvmadhav", "img_url": "https://pbs.twimg.com/profile_images/2048284096229670912/3n1wdkfP_normal.jpg"}}