For me, the biggest hurdle to writing a PWA is the insane installation process [1]. There are also a ton of quirks, eg I don’t think you can update the icon if it’s installed as a PWA. It is hard to argue that this whole process has not been hobbled intentionally.
Anyone know why OpenAI hasn't released a new model for fine tuning since 4.1? It'll be a year next month since their last model update for fine tuning.
For me the issue is why there's not a new mini since 5-mini in August.
I have now switched web-related and data-related queries to Gemini, coding to Claude, and will probably try QWEN for less critical data queries. So where does OpenAI fits now?
I think they just did that because of the energy around it for open source models. Their heart probably wasn't in it and the amount of people fine tuning given the prices were probably too low to continue putting in attention there.
Also interested in this and a replacement for 4.1/4.1-mini that focuses on low latency and high accuracy for voice applications(not the all-in-one models).
For me, Codex does well at pure-coding based tasks, but the moment it involves product judgement, design, or writing – which a lot of my tasks do – I need to pull in Claude. It is like Claude is trained on product management and design, not just coding.
For someone looking to switch over to Gemini from OpenAI, are there any gotchas one should be aware of? E.g. I heard some mention of API limits and approvals? Or in terms of prompt writing? What advice do people have?
I use a service where I have access to all SOTA models and many open sourced models, so I change models within chats, using MCPs eg start a chat with opus making a search with perplexity and grok deepsearch MCPs and google search, next query is with gpt 5 thinking Xhigh, next one with gemini 3 pro, all in the same conversation. It's fantastic! I can't imagine what it would be like again to be locked into using one (or two) companies. I have nothing to do with the guys who run it (the hosts from the podcast This day in AI, though if you're interested have a look in the simtheory.ai discord.
I don't know how people use one service can manage...
I emailed support a while back to see if there was an early access program (99.99% sure the answer is yes). This is when I discovered that their support is 100% done by AI and there is no way to escalate a case to a human.
Me: Is it possible get early access to the GPT 5 fine tuning? It is much better at non-English languages, which is the majority of what we do, so it would be greatly beneficial to us.
Bot: I'm an AI support agent. I don't have information about early access to GPT-5 fine-tuning or unannounced features. Currently, there is no public information or program for early access to GPT-5 fine-tuning. Please keep an eye on official OpenAI channels for updates. Let me know if you have any questions about current features or products!
Me: Can you ask someone from the team if I can be part of the early access? I know there is no public information, but there is an early access program and I would like to be part of it.
Bot: I'm an AI support agent and do not have the ability to forward requests or make inquiries about early access programs with the OpenAI team. If early access becomes available, it will be announced through official channels. Let me know if you have any other questions about OpenAI products or current fine-tuning options.
Me: How do I get in touch with the open ai team?
Bot: I'm an AI support agent and can only assist with OpenAI products or services through this support channel. There is no separate contact method for the OpenAI team beyond official support and public announcements. If you have questions about current products or features, I'm here to help
You're talking about a model that will notoriously refuse to say a racist word even if you tell it that it's the only way to prevent a nuclear apocalypse.
You don't have to like it, but the global menu bar is at the top of the screen which means you just fling the mouse to the top and then go left or right, instead of having to get to the right vertical.
True. This could be nicely solved by placing a non-global window all the way at the top of the window, so that you can still fling the cursor to the top of the screen if the window is maximized or otherwise along the top edge of the screen.
I want to say it (or something similar at least) was originally addressed by from __future__ import annotations back in Python 3.7/3.8 or thereabouts? I definitely remember having to use stringified types a while back but I haven't needed to for quite a while now.
It turns them into thunks (formerly strings) automatically, an important detail if you're inspecting annotations at run time because the performance hit of resolving the actual type can be significant.
