_betty_

what do servers/proxies do when they don't recognise the verb?

no because it's linux running in windows not the other way around.

isn't that a completely different use case? messages to Claude from other sources vs from Claude when it's finished?

hooks can already alert you and have flexibility

https://github.com/vercel-labs/skills/issues/12

Having only used the base price of each, I loved the ux of cursor and what it enabled me to do, but I hit my monthly cap in 2 days. Whereas Claude code (on pro) I do hit my session limit and even weekly limit once but never have I had to been tools down for 20+ days.

I hear codex is even more generous.

Admittedly all seem cheap enough, but there does seem to be a large diff in pricing

Daniel Pink's book "Drive" explains that true motivation comes from intrinsic factors: autonomy, mastery, and purpose. It’s not about external rewards or doing every task yourself, but about having the freedom to direct your work, the drive to improve your skills, and a meaningful purpose behind what you do. In programming, AI can free us from routine tasks, letting us focus on creative problem-solving and realizing our ideas - this aligns perfectly with what Pink calls the deeper, more fulfilling motivation to get things done in a way that matters. So, it’s less about losing fun and more about shifting to meaningful engagement and impact.

ooh that's interesting, wonder if that works better than git eorktrees when playing with multiple AI agents

VS Code plugin seems to be missing quite a number of the CLI features.

how about requiring some kind of interaction if they want to run an install script?

They now compete in a larger market - non vscode users

I like that I can use the ide while a cli is working, keep an eye on git changes and interrupt where needed.

I find in ide they like opening documents/changing tabs too much and it means j can't do other things.

It's from July 6, so yeah a month in the past is totally right.

She has newer posts on sub agents

interesting, i had just watched Primeagens Standup with Adam and got the impression they don't do well for money, but a quick google came up with a bunch of posts from Adam himself disclosing some fairly impressive numbers.

No idea if he still does ok from it, but he certainly did at one stage.

would they still be able to charge for it if it was an lsp?

Also just how separate the tool was - it was the primary reason I checked out the product but felt I had to go searching to find it.

Maybe a add to canvas/project button in the code gen area.

Lack of tools (shapes, cards etc)

Also felt very laggy/buggy when selecting, dragging etc. may be my underpowered rig

Canvas is an interesting idea - although the implementation feels very clunky and half finished.

rest of the tool doesn't feel that special - eg there's tonnes of code generators out there. would have to play more to understand but it wasn't immediately apparent

i've been dreaming of a way that visualises the user flows in the software (rather than cards on a board), think spider map showing possible user flows then colour coded circles based on what stage they're in.

that way you can see what state an entire flow is in at a glance and being able to co-ordinate effort accordingly.

i did something similar with a vodafone phone like 3 times, they just kept giving me the same model again and again.

interesting, they could finally deprecate the form attribute on buttons...

https://simonhearne.com/2020/drop-ev-certs/

they normally require a revocation lookup on the spot, and iirc there was differences in if they could or how stapling worked.

they were also pretty bad for performance due to the extra lookup (and reduction in caching)

this is one of the things i love about azure, easily being able to see everything.

closest i found in aws was something like tag manager?

for me i can auto-gen basic validation from either my typescript or graphql type. Then fairly easily extend it manually.

yeah i could do it manually, but the integration with other tools was the killer.

Foreach in razor is just c# too, so it's not a language thing it's more what it transpiles to.

knowing both i used to be frustrated by jsx's lack of support for plain if and for loops like razor has (eg map and the weird && syntax we general end up with)

eg ``` <ul> @foreach(var item in list) { <li>@item.name</li> } </ul> ```

of course this idea goes against jsx's implementation (as it's just nested functions) and paradigm of being html in plain javascript rather than an interpreted templating language.

some of the differences i really like (like being able to assign compoents to variables, pretty sure razor doesn't have anything like that).

Almost feel like it'd make more sense to merge with another tool, like tldraw

agreed. i've specifically disabled it. unfortunately i imagine the option will dissapear eventualy.

I see you can start linking things to urls/files, curious as to if this will unlock developers adding more metadata to designs which might eventually be nicely displayed in Figma.

I have a desire to try Figma out as a project management tool, as in being able to easily visualize which screens/flows have been implemented by a developer, which ones have been updated since. I believe Figma is a good tool for that as it is visual and often already used to show things to clients.