On Max plans, premium seats on Team plans, and premium seats on legacy seat-based Enterprise plans, Fable 5 will be a standard part of your plan.
HN user
tidbeck
Guess it is efficient for attention.
Related to this, for our use case, setting thinking to high instead of low made tasks complete faster and cheaper (Gemini 3.0 flash).
Other aspects are caching, often at 0.1X cost, where providers really differ in how efficient they are (Anthropic really good, Google not so much) and how chatty a model is (costing output tokens).
I really like this but feels like it does not really work on a Swedish keyboard layout (macOS), cannot input '$'. Tried both Alt+4 (how you actually input '$') which works in vim and Shift+4 (US layout).
While the accessibility tree is great in many aspects it has its own limitations for example when it comes to stacked views or lazy loading outside the viewport.
Looking at the examples on the front page it reminds me even more about Parse.
The Reuters article title is "Fabric made of Stone" (as it is made of coal and limestone), that is why it came to mind.
This makes me think about Vinylon[1] and this article from Reuters[2]
[1] https://en.wikipedia.org/wiki/Vinylon [2] https://www.reuters.com/investigates/special-report/northkor...
Got a https://en.wikipedia.org/wiki/Leisure_Suit_Larry#Leisure_Sui... vibe from it.
What kind of tasks do you use it for?
How does this compare to https://huggingface.co/ibm-granite/granite-docling-258M in performance and how they work?
That is why I like the idea of having as much of the documentation as possible in code. Tests that describe how things are supposed to work, infrastructure as code the describes the parts of the system and so on. Then you are forced to keep them up to date.
Still seem to be down, a link for status updates: https://status.claude.com/incidents/6xlfx3mrb8ct
I have (Firefox on macOS), still easy to miss.
This is different from the Minimum Deployment, which I current have set to iOS 12.0 in Xcode 16.2.
Could you maybe make use of Simon Willsons [LLM lib/app](https://github.com/simonw/llm)? It has great LLM support (just pass in the model to use) and records everything by default.
https://devenv.sh/ and Dev Containers are not the same thing.
I also prefer native clients so I have been using the https://mimestream.com/ beta and it has been working great for me.
Vimium (for Firefox at least) supports custom search engines so you can do:
og<space> my-search<enter>
'o' for open and 'g<space>' to select Google as search engine.
I had the same issue but your comment made me look up if there is something to do about it. Both things are possible https://github.com/ohmyzsh/ohmyzsh#getting-updates