..

133 posts

.. banner
..

..

@tesseractcode

i post ai and prompt ai like a mf

South yorkshire 加入时间 Mart 2020
45 关注25 粉丝
..
..@tesseractcode·
elon i know must change that cursor name somehow
English
0
0
0
3
..
..@tesseractcode·
Codexmaxinggg this weekend like a mf
English
0
0
0
7
..
..@tesseractcode·
@mirochill Hmmm okay let’s see how it goes
English
0
0
1
90
Mirochill
Mirochill@mirochill·
🤯 LEAK : GPT 5.6 Pro est vraiment impressionnant ! En seulement 30 minutes, il m’a généré une fusée ultra détaillée en voxels, capable de décoller, avec une caméra qui la suit, des effets visuels, et même du son généré procéduralement ! 🚀
Français
7
21
300
15.8K
..
..@tesseractcode·
@jasperdevs I’ve been crying all day on the timeline. This is not an improvement to what we have if frontend is not fixed. 5.5 is a great model at coding already
English
0
0
1
312
..
..@tesseractcode·
@mirochill I need to know the skills, unbelievable that I don’t see rounded cues and pills
English
1
0
2
127
..
..@tesseractcode·
@benhatch44 I’ll def do loads then. Let’s see I’ll update you 🙂
English
0
0
1
32
Ben Hatch
Ben Hatch@benhatch44·
I am officially giving up on my first app It's the first iOS app I launched and I learned a ton through the process But it has garnered less than 200 downloads and less than $100 revenue since launch last year I will be going all in on my second app, SoberQuest, which has gained much more traction: Over 600 downloads Over $600 in revenue New users coming in daily RIP Mandu 💔
Ben Hatch tweet media
English
74
1
244
38K
..
..@tesseractcode·
@thegenioo Honestly I use gpt5.5 and even when I give it screenshots and it has all the vision in the world I still fight with it every damn day. I’m def trying glm5.2. Heard it tops fable for frontend
English
1
0
1
429
Hamza
Hamza@thegenioo·
GLM-5.2 is seriously underestimated because it doesn’t have vision, but honestly, the model is too good. No open-source or Chinese model has been this reliable or clean when it comes to implementing plans and doing real work. The only thing it really lacks is vision, but that doesn’t make it a bad model.
English
18
5
135
10K
Satya
Satya@heysatya_·
Thinking of building my own app. Got any app ideas? And if you’re building something cool already, I’d love to join and help with design, product, and growth.
English
125
3
280
26.1K
Kilo
Kilo@kilocode·
Everyone benchmarks GLM-5.2 against the frontier now. So we did too. We pulled GLM-5.2's plan up against Claude Fable 5's, the plan that won our last frontier round. Same prompt, same task, same rubric. Fable scored 9.1. GLM-5.2 scored 9.0.
Kilo tweet media
English
96
151
2.1K
188.2K
..
..@tesseractcode·
@BradGroux I get 5.5 analyse my codebase on local using MCP then or push to GitHub so 5.5 pro can see. Then ask it to create markdown prompt of task for codex and also generate a small goal prompt. Works like magic!
English
0
0
3
26
Brad Groux
Brad Groux@BradGroux·
Codex writing your goal prompt is amazing. Even better, have it save the prompt to a markdown file, so you can exceed the 4000 character limit. Ex: Create a /goal prompt to complete the backlog, and save it as a markdown file. /goal complete the prompt in the markdown file.
English
23
9
149
14.6K
.. 已转推
OpenAI
OpenAI@OpenAI·
As AI takes on longer, higher-stakes tasks, we want models to carry beneficial and safe behavior into new domains beyond their training—and maintain it under pressure. That’s the idea behind our new research on training models to be broadly and persistently beneficial. alignment.openai.com/beneficial-rl/
English
187
238
2.6K
295.4K
..
..@tesseractcode·
@R2Cdev_ If true then it’s beyond trash
English
0
0
1
381
Raphi-2Code
Raphi-2Code@R2Cdev_·
GPT-5.6 Pro SVg - Le Chaton Fat
Raphi-2Code tweet mediaRaphi-2Code tweet media
Deutsch
7
5
194
7.8K
..
..@tesseractcode·
@mirochill What’s gpt obsession with rounded edges and cards? !
English
0
0
1
383
..
..@tesseractcode·
@LexnLin Very disappointed
English
0
0
0
411
.. 已转推
Chetaslua
Chetaslua@chetaslua·
🚨 Breaking News OpenAI is testing multiple 5.6 series of model , i got access so be online and active will drop lots of test and comparisons and also you can comment hard prompt and your fable result on that we will compare with 5.6 Pro
Chetaslua tweet media
English
87
99
1.7K
287.7K
Seb Johnson
Seb Johnson@SebJohnsonUK·
A UK startup can now assess skin cancer from a smartphone! People have been talking about using AI to cure cancer. This is the first time I've seen a company actually come close. Users take a close-up photo of a mole or lesion through the app and it returns one of two results: clear, or a referral for further assessment. The same decision a dermatologist would make but made autonomously by an AI on a consumer device. The technology has already been used on 230,000 patients and identified over 20,000 cancers, but this is the first time it's being used on a smartphone. CRAZY, amazing stuff from the team at @SkinAnalytics
Seb Johnson tweet media
English
34
50
455
102.1K