ND (@Neil_Dagger) header
ND (@Neil_Dagger) profile picture

Full time tinkerer of AI tools and agents. Author of The ChatGPT Millionaire. Building https://nitter.cf/t.co/wAadwdFWKM - Your personal AI council.

London
Joined January 2009
Claude code is badly vibe coded. It's pathetic how bad the UX is, no UAT at all it seems.
57
The most garbage update in the history of OpenAI - seriously I want full screen chats back ! It'd be fine if Chatgpt.com on browsers wasn't an insane memory leak that loaded insufferably slow in long threads.
56
Why this hell does this never work
31
The Codex Mac app has so many visual bugs.
42
Updated Mythos / Fable benchmarks.
25
If buying isn't owning, then pirating isn't stealing. Have fun everyone, Fable is on Piratebay.
92
Replying to @andrewmccalip
I'd like to be able to see all the blocks, please, and maybe some way to confirm that the tagline's been edited.
2
345
Replying to @andrewmccalip
I'd like to be able to see all the blocks my ads are showing on please, please.
1
2
619
Definitely the most dystopian part of Claude Mythos / Fable 320-page system card is the "Health admin bench", where they tested, presumably, a feature for insurance companies to more easily deny claims. Amazing.
1
134
I used Fable to create a typefully.com and superx.so clone - it only took like 2 hours - that includes getting the corpus of tweets from huggingface and finetuning them (all done by Claude Code of course)
78
Hitting the 5 hour codex limit in 25mins on the Pro 5x plan? Literally 2 sessionsed used up 38% of my weekly allowance it's mental something is wrong. Ok I was spoilt by using the 10x boost on the 20x plan from the meetup but still!
1
2
220
Replying to @nicdunz
28.3B in the last 3 months.
1
113
Running a 50 agent systematic debugging trace usinf claude code workflows
1
42
My rate limits are ending in about eight hours, so I decided to run a bunch of workflows. Check out this one: a 19-way vote on every single line for my pricing page for CRO optimization.
We've reset 5-hour and weekly rate limits for all users on Pro and Max plans. We fixed an issue that caused some Claude Code sessions to spawn excessive parallel subagents, burning through usage faster than expected.
50
Claude code app is such a janky bad ux peice of shit without any proper testing - tell me how eactly "I've hit my session limit" when it clearly says its only 22% used. Combined with a worthless support team it's such a travesty to use.
1
1
252
tokens - I like my streak tbh.
1
90
Ok so Opus 4.8 is absolutely awesome at front end design (though I did ask it to get a second opinion from 4 parallel models as well as codex to fit any ux banks)
1
1
1
108
Doing UAT with Claude code/Codex is great but you end up with this
1
60