Anthropic's Claude chat interface at claude.ai and iOS/Android apps; public access first opened alongside the Claude 2 model launch.
Specific experiences are worth more than sweeping claims.
@hn_849d71
4 months ago
Public discussion, not a rating submitted on Rate My AI.
Awesome improvements, but compared to Claude Artifacts, it lacks the html/js "Preview" where you can run the code and check/validate the result without leaving the browser. This is a killer feature
@hn_71962f
4 months ago
Public discussion, not a rating submitted on Rate My AI.
I like to prompt Claude to create artifacts in plain HTML, CSS and JS. I like the portability and hackability of these. React is too heavy for a lot of simple ideas even if reactivity is needed.
@hn_5a0b10
4 months ago
Public discussion, not a rating submitted on Rate My AI.
I've been pretty happy lately with my setup. Arc browser lets you hover over a link to show a card that summarizes the article. With Claude Projects, I'm able to quickly build an Arc "Boost" User Script for any site, so I have one to export the HN homepage to JSON to import into an LLM. And I have one on comment pages to do the same. I have a userscript to remove pagination so I can infinitely scroll and then export. Ad I have a Claude Project specifically for identifying/categorizing comment threads by the patterns of knowledge crystallization etc. It's been fascinating so far.
@hn_0bdc65
4 months ago
Public discussion, not a rating submitted on Rate My AI.
This is the most interesting aspect to me. I had Claude generate a guide to all the gyms in Pokemon Red and instructions for how to quickly execute a play through [0]. It obviously knows the game through and through. Yet even with encyclopedic knowledge of the game, it's still a struggle for it to play. Imagine giving it a gave of which it knows nothing at all. [0] https://claude.site/artifacts/d127c740-b0ab-43ba-af32-3402e6
@hn_320429
4 months ago
Public discussion, not a rating submitted on Rate My AI.
Skills can be toggled on and off, which is good for context management, especially on larger / less frequently needed skills Currently if a project is 5% or less capacity, it will auto-load all files, so skills also give you a way to avoid that capacity limit. For larger projects, Claude has to search files, which can be unreliable, so skills will again be useful for an explicit "always load this"