eigenhaunt

103 posts

eigenhaunt banner
eigenhaunt

eigenhaunt

@eigenhaunt

NP-hard to deal with

Reading, England Katılım Nisan 2026
137 Takip Edilen4 Takipçiler
eigenhaunt
eigenhaunt@eigenhaunt·
If you want to use your iPad Pro with the keyboard, why are you even buying it?
English
0
0
0
5
eigenhaunt
eigenhaunt@eigenhaunt·
@cyberboydanny @Rasmic Disagree. The stability of Codex was evident from the very early Alpha releases. I have been using since. Always had more confidence using codex but opus 4.5 4.6 gave me better confidence, now back at codex for now
English
0
0
0
8
eigenhaunt
eigenhaunt@eigenhaunt·
@Rasmic There are a lot of things in world you unknowingly hate because you hate some people
English
0
0
0
7
eigenhaunt
eigenhaunt@eigenhaunt·
@Rasmic Honestly, Tibo's this behaviour could be the only reason atm to hate Codex.
English
4
0
1
1.8K
Mark Kretschmann
Mark Kretschmann@mark_k·
It’s supremely ironic that good writing turns out to be one of the hardest problems for "Large Language Models".
English
49
5
195
12.1K
Mimi
Mimi@candlighter·
@trq212 Correct, also ditched PowerPoint and word for html
English
1
0
0
257
Thariq
Thariq@trq212·
HTML is the new markdown. I've stopped writing markdown files for almost everything and switched to using Claude Code to generate HTML for me. This is why.
Thariq@trq212

x.com/i/article/2052…

English
892
1K
12.1K
4.4M
eigenhaunt
eigenhaunt@eigenhaunt·
@JinjingLiang I agree Gemini is not trusted in coding but man it is the smartest writer try chatting it with
English
1
0
1
121
Jinjing Liang
Jinjing Liang@JinjingLiang·
A few months ago someone from Anthropic told me that they were afraid of Google, not OpenAI Now I get it. Gemini below:
Jinjing Liang tweet media
English
15
1
115
18K
eigenhaunt
eigenhaunt@eigenhaunt·
at this point opus is only doing ui refinements on top of 5.5 implementations
English
0
0
0
11
sysls
sysls@systematicls·
It's so interesting to me how drastically different the personalities of Opus 4.7 and GPT 5.5 are. GPT 5.5 is smart, hardworking, slightly autistic and doesn't want to talk much. Huge preference for diving into tasks and hammering tasks out over long, long periods. Opus 4.7 is also obviously smart, but the only way to accurately describe Opus 4.7 is that he is charismatic but extremely lazy, talks a lot, but doesn't like to get work done. The only saving grace of Opus 4.7 is that he really does have an eye for design. -- Opus 4.7 is the quintessential toxic employee you need to fire while GPT 5.5 is the one you're glad to have on the team, but wished you could understand him better / have a more pleasant time interacting with him.
English
123
71
1.5K
196.6K
eigenhaunt
eigenhaunt@eigenhaunt·
Frontend taste of opus 4.7 is still unmatched
English
0
0
0
12
eigenhaunt
eigenhaunt@eigenhaunt·
@thegenioo Non thinking is not close to opus non thinking
English
0
0
1
2.1K
Hamza
Hamza@thegenioo·
Is 5.5 Instant at the level of 4.7 Opus (non thinking) or better?
English
23
3
147
42.1K
eigenhaunt
eigenhaunt@eigenhaunt·
Guess what if those saints knew we are in simulation and that’s why they decided to do nothing and said nothing matters
English
0
0
0
13
Sick
Sick@sickdotdev·
openai: fun anthropic: anxiety
English
30
5
61
3.1K
eigenhaunt
eigenhaunt@eigenhaunt·
@rxhit05 Strength is high IQ model, still lacking in functionality.
English
0
0
0
10
Rohit
Rohit@rxhit05·
Do you all think codex can actually replace Claude Code?
English
79
1
70
5.9K
Audiencon⚡️
Audiencon⚡️@audiencon·
If you could only keep one AI subscription, what would it be and why?
English
15
0
7
1.2K
Can Vardar
Can Vardar@icanvardar·
i use codex btw
English
31
2
111
4K
Vishal
Vishal@vishaltweetup·
If AI writes 90% of the code, what do we call developers now?
English
124
4
85
7.1K