To be fair, most coding agent cli's by the labs do this and are opt in by default, it's just this does too
HN user
treexs
Ahh been working on the same thing for a while now but haven't launched yet
Wow everyone on HN seems very out of touch with Cursor.
Their UX on their agents only window is quite good and on par if not better than Codex and Claude desktop apps and it still has quite a good bit of subsidization especially with Composer 2.5 being on par with Sonnet at the very least. They're also growing tremendously this year to 4B ARR recently on track to go higher before EOY.
codex generated sites are so easy to spot lmao
I thought Apple does tell you how long they'll support hardware.
For example: https://support.apple.com/en-us/102772
With the hiring 1111 interns thing, I think these companies (amazon as well) need to realize this is doing anything but inspiring confidence in those interns. Instead of being excited about going there, more of them would opt to go elsewhere instead of returning full time, or if they do return full time they'd be in fear of being let go next.
interesting, but I really wonder how big the audience is of people wanting to know their fortune while claude coding within the claude code interface
for what it's worth the creator mentioned this site was made in a couple of minutes lol
Woah very cool, yeah I think the cards and heading/subheading structure is very similar to what codex outputs, but I can tell the different visualizations definitely require your own personal touch
I feel like I've gotten really good at noticing which model generates what type of site and this oozes codex
this is the plot of Persona 5
Vercel very clearly highlights that you need to redeploy once you make a credential change
well yeah since they tell claude code the business decisions and it creates the comments
Yes it's the claude code CLI tool / coding agent harness, not the weights.
This code hasn't been open source until now and contains information like the system prompts, internal feature flags, etc.
does this not work? https://www.mintlify.com/samarth777/claude-code-copilot/intr...
won't they just try to dmca or take these down especially if they're more popular
The big loss for Anthropic here is how it reveals their product roadmap via feature flags. A big one is their unreleased "assistant mode" with code name kairos.
Just point your agent at this codebase and ask it to find things and you'll find a whole treasure trove of info.
Edit: some other interesting unreleased/hidden features
- The Buddy System: Tamagotchi-style companion creature system with ASCII art sprites
- Undercover mode: Strips ALL Anthropic internal info from commits/PRs for employees on open source contributions
Was experimenting with it but it felt like it'd have higher latency, and it seemed more feasible to do eyetracking on a single screen than across screens, especially with different webcam layouts and stuff
?
hundreds of local llm apps exist
the what's next section acts novel but all of them have been achieved or created in some format already: you can run a local llm on a phone and connect it to a agent
it gets to a point
wow it's interesting how noticeable sites built with claude maybe with the frotnend-design skill are now
Asking the company that is banning use of their subscription in other services, when other subscriptions like Codex and OpenCode don't, to make something that is interoperable with similar systems. Alright lol
ty! It fetches from the api so it technically shouldn't run out, tried to fix the issues with it prefetching repos so feel free to give it a shot now
Feel free to suggest it on the site here: https://aicoderlist.vercel.app/add
Yeah my bad. Overhauled it a little, and you can now suggest on the site here: https://aicoderlist.vercel.app/add
Thanks for making jpdb! Even without your srs system, just the catalogue of media and difficulty ratings has been monumental for immersion.