IngoA (@ingoa_dev) header
IngoA (@ingoa_dev) profile picture

I'm doing the thing w mobile apps.

Yourope
Joined November 2022
Photo by IngoA (@ingoa_dev)Photo by IngoA (@ingoa_dev)Photo by IngoA (@ingoa_dev)Photo by IngoA (@ingoa_dev)Photo by IngoA (@ingoa_dev)Photo by IngoA (@ingoa_dev)Photo by IngoA (@ingoa_dev)Photo by IngoA (@ingoa_dev)Photo by IngoA (@ingoa_dev)Photo by IngoA (@ingoa_dev)
Quick check on paywall, plan mix, trial. No changes: 4.9% install โ†’ paid is ~2ร— the soft-paywall median; traffic is the bottleneck. Could try hard paywall later, but it's an app change. Sucks that this has gotten risky and slow.
I'm in. Got me this glaring beauty for it ๐Ÿš€ Let's do boring marketing all month! I guess it will be exciting, so much to learn ๐Ÿ”ฅ
1
41
Also app choice - let's call it APP A :)
6
I'm in. Got me this glaring beauty for it ๐Ÿš€ Let's do boring marketing all month! I guess it will be exciting, so much to learn ๐Ÿ”ฅ
I'm starting end-of-year marketing hackathon and I encourage everyone to join it! The reason for this challenge is that I've decided to stop active marketing my other apps and focus 100% on 1 app only pushing it as hard as possible to see where I could get by the end of the year. Decided to share this so others can get that extra boost of motivation and do their best until Christmas and then finally enjoy well-deserved rest. There're no prizes on this hackathon. No hidden marketing. No paid advertising. Free entry for everyone. If you cheat, you're only cheating yourself. Up to you, I don't care. If no one joins me, I don't care either, as I'm doing this challenge for myself, but ofc I encourage everyone to participate. At the end of the challenge, the winner gets... a virtual pat on the back from me ๐Ÿ˜„ Here is the link btw: finalpush-alpha.vercel.app/
1
1
1
80
Starting value is very close to @Aivars_Meijers , but he is a social media master ๐Ÿ‘‹
11
Classic Google.
2
110
I'm starting end-of-year marketing hackathon and I encourage everyone to join it! The reason for this challenge is that I've decided to stop active marketing my other apps and focus 100% on 1 app only pushing it as hard as possible to see where I could get by the end of the year. Decided to share this so others can get that extra boost of motivation and do their best until Christmas and then finally enjoy well-deserved rest. There're no prizes on this hackathon. No hidden marketing. No paid advertising. Free entry for everyone. If you cheat, you're only cheating yourself. Up to you, I don't care. If no one joins me, I don't care either, as I'm doing this challenge for myself, but ofc I encourage everyone to participate. At the end of the challenge, the winner gets... a virtual pat on the back from me ๐Ÿ˜„ Here is the link btw: finalpush-alpha.vercel.app/
23
3
7
114
12,493
IngoA retweeted
show this video to anybody that is an old school programmer that hates AI this is one of the best videos Iโ€™ve seen all month.
1,107
6,400
1,313
46,656
4,077,975
Replying to @Gegam245074
It is like when you use cheat codes for a game. The game instantly becomes boring. A.I. is like cheat codes for everything.
2
1
23
2,053
We finally found the reason for 1-star reviews - Android seems mostly set to RTL ๐Ÿ˜…
I always wonder about those app reviews from Arabic-speaking countries. Do they pick stars from right to left because of RTL, or are they just trolling me? ๐Ÿ˜…
2
2
557
Hey @AnthropicAI , nobody is impressed with Fable 5.5-3. Now give back ressources to Opus 5.5, we need to work.
2
192
my model tier list this is every model i use right now i still think opus 5.5 is better overall than fable 5.2, it's just so consistent and the limits are great gpt 6 astra is retired, i don't use it at all
1
133
IngoA retweeted
quick question, what the fuck
Background subagents in Claude Code now use less of your usage limit. A running subagent updates its status line every 30 seconds, and each update used to re-read its whole conversation. Now Haiku 5.5 writes it from short notes instead, so each update costs about 99% less.
50
75
4
5,247
477,035
Supposedly this does not work anymore since last Codex update. I overheard a prompt that may fix it, in the replies.
everyone thinks codex computer use only works inside codex it doesn't, it's a local mcp server in the chatgpt mac app and claude code can just call it, even headless with claude -p same 8-task test: opus 5.5 on codex's engine got 6/8, codex itself got 6/8, cua driver got 3-4/8 at 4x the cost cua's background mode on mac only goes through accessibility, so canvases and drags just don't land codex's engine sends real clicks and drags to the app without touching my cursor no hover though, and it's unofficial, so enjoy it until a chatgpt update breaks it give this to your claude: "Set up Codex's computer use as an MCP server for you on my Mac. Find the "cua_repl" entry in ~/.codex/plugins/cache/openai-bundled/unified-computer-use/<newest version>/.mcp.json and register it as a user MCP server called "codex-cu" with the same command, args and env. Then test it by using Calculator in the background to work out 12 ร— 12."
2
1
3
326
Rename the helper .app so Spotlight can tell it apart. Copy the plugin's .mcp.json and repoint every ChatGPT.app and ~/.codex path, including require-browser-access.mjs. Set CODEX_HOME, CODEX_CLI_PATH, PATH, SKY_CUA_SERVICE_PATH and SKY_CUA_SERVICE_NATIVE_PIPE_PATH.
1
36
Run the helper from a LaunchAgent with those same vars. It needs codex itself, or you get -10005 "app-server exited". The private socket lets it run beside ChatGPT's helper. Test by driving an app, not listing tools: ChatGPT closed, ChatGPT open, then after a reboot.
21
The Aliens edit each other now.
We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math. It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training. We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! ๐Ÿงต Blog: rikiyat.github.io/blog/weighโ€ฆ
Readers added context they thought people might want to know
LLM was given weights explicitly as text in prompt and used code/forward passes (per authors' logs) to ablate Qwen looping direction, a known thinking-mode issue per model card. Primarily fixed repetition in that mode, not general 'natively' improving weights/math. rikiyat.github.io/blog/weight-spโ€ฆ github.com/RikiyaT/lm_undโ€ฆ huggingface.co/Qwen/Qwen3.5-0โ€ฆ huggingface.co/RikiyaT/Qwen3.โ€ฆ
113
I'm talking to my therapist right now. Fun app, japan only ๐Ÿคทโ€โ™‚๏ธ
I really hate that I cant build new apps. Building apps was therapy for me. Im having an existential crisis.
1
203
Opus being lazy and dumber for me since yesterday, anyone else, did the nerf begin?
2
4
246
Hopefully it's just the Fable 5.5 release coming up.
1
104