Well, Claude does boast an absolutely cursed (and very buggy) React-based TUI renderer that I think the others lack! What if someone steals it and builds their own buggy TUI app?
I think that’s a real problem now. In our parliament (Czech) almost every politician is a lawyer or a doctor. Almost no other profession is represented.
the ux feels extremely similar down to the elicitation ... but I did some more research ... they were started independently in april 2025. Therefore, one being a fork of the other is almost impossible and there is no evidence for it. Also, opencode is in go and gemini is in typescript.
Sadly my above misinformation can no longer be edited.
So you would deny children the greatest source of knowledge in the history? I have learned math and programming thanks to unlimited access to the web and would not be where I am without it.
First of all, you cannot know that, since plenty of people before you learnt that stuff from libraries.
>So you would deny children the greatest source of knowledge in the history?
Yes, because other sources of knowledge exist and are much more appropriate for children. It is also the greatest source of despicable stuff in history. When you turn 18, have fun exploring the world wide web.
I still remember gemini 1.5 ultra and gpt 4.5 as extremely strong at some areas that no benchmark capture. It was probably not economical to use them at 20 usd subscription, but they felt differently and smarter at some ways. The benchmarks seems to be missing something, because flash 3 was very close on some benchmarks to 3 pro, but much, much dumber.
Not sure what you mean. It IS the same model, just a smaller version of it. And gpt-5.3-codex is a smaller version of gpt-5.3 trained more on code and agentic tasks.
Their naming has been pretty consistent since gpt-5. For example, gpt-5.1-codex-max > gpt-5.1-codex > gpt-5.1-codex-mini.
what do you mean by the same model, just smaller version? Codex should be finetune of the "normal" version, where did you get it's smaller? It's not that simple as to take some weights from the model and create a new model, normaly the mini or flash models are separately trained based on the data from the larger model.
What was the reasoning about not implementing vertical tabs much, much earlier? I use them now in the canary builds, but on 4k 32" screen it is not that critical as it was on the small 16:9 full hd screen. The vertical space used to be much scarcier than the horizontal.
When we started work on Chrome my favourite browser was a now-forgotten IE shell called iRider, which implemented tree-ish style tabs in a better way than anyone, and we did take multiple attempts at vertical tabs early on.
We didn't ship them because they were only a mitigation of the too-many-tabs problem, not a solution, and they didn't really fit our model of 'tabs are titlebars'. They were also never going to be default - most people did not have that many tabs, and we had a very strong opinion was that we shouldn't have configuration - it was better to very strongly execute on one vision we loved and risk losing people (but hope the quality would bring people along), than to execute and support multiple directions poorly.
The world has changed a lot since I last worked on Chrome ten years ago, so as an outsider I'm excited to see what the team currently attempting it can do.
reply