Zan (@Sodanzen) - Twitter Profili | Zamantika Mersobahis Locabet

Zan@Sodanzen·6d

Build a tool that can solve the paradox of you can "outsource your thinking but you can't outsource your understanding" @karpathy

English

0

5

Zan@Sodanzen·6d

@borjafat seo

0

4

borja@borjafat·30 Nis

Claude Opus 4.7 or GPT-5.5 can run your ENTIRE SEO Tired of chasing backlinks? Solved. Tired of AI slop articles? Solved. Tired of ranking for keywords that don't convert? Solved You just install a SKILL and you're ready to roll. Can run automated daily tasks on a schedule Comment "SEO" and I'll send it!

English

890

40

601

64.3K

Zan@Sodanzen·26 Nis

@kcosr Awesome - this is how it need to be -

English

0

1

522

Kevin@kcosr·26 Nis

Look mom, no hands.

English

13

7

454

46.5K

Zan@Sodanzen·19 Nis

@elliotarledge Claude is now behaving much like gemini - just unhinged - everything needs to be done on plan mode first

English

0

80

Elliot Arledge@elliotarledge·18 Nis

just woke up to opus 4.7 nuking one of my projects during an overnight session. luckily i was able to get it back easily

English

70

16

532

103.6K

Zan@Sodanzen·18 Nis

@gdb Totally, leaves Claude behind in all metrics atm

English

0

1

68

Greg Brockman@gdb·18 Nis

codex makes work plain fun

English

190

50

1.8K

103.4K

Zan retweetledi

Sarah Chieng@MilksandMatcha·16 Nis

x.com/i/article/2044…

ZXX

31

52

585

288.6K

Zan@Sodanzen·16 Nis

@theo The problem when you try and be all and everything all at once

English

1

0

1

142

Theo - t3.gg@theo·16 Nis

I can't stop looking for more issues. I'm addicted. It's like an easter egg hunt but the eggs are all oddly shaped and smell bad.

Theo - t3.gg@theo

I feel bad dunking on them so much but it's genuinely absurd how bad the new Claude Code desktop app is. You can feel the vibe code leaking everywhere. Every "feature" is barely integrated and full of edge cases that weren't considered. Every menu feels barren, stuffed in last second for some random toggle. Every hotkey breaks as soon as you try to do anything else. I've lost track of how many bugs I've encountered. I found at least 40 in under an hour. And it's all truly absurd arcane shit. Stuff like voice mode typing in all input boxes instead of just the one you have focused. Any one of these issues would have been enough for me to do a massive post-mortem and likely fire someone. A $400b company shipping this is absurd. I feel like I'm going mad. How does anyone seriously use this?? It is broken on fundamental levels that are hard to comprehend. How are we supposed to trust the code these models produce if Anthropic's official showcases are absolute slop? Dedicated video on this coming tomorrow. Just needed to get this off my chest.

English

41

11

486

30.9K

Zan@Sodanzen·14 Nis

@romainhuet @haydendevs Codex CLI just rules man - just wow atm.

English

0

34

Romain Huet@romainhuet·14 Nis

@haydendevs It’s come a long way, and we’re improving every day! Curious what you think if you try the Codex app: openai.com/codex/

English

12

1

89

2.8K

hayden@haydendevs·14 Nis

is codex good now?

English

115

0

205

26.1K

Zan@Sodanzen·12 Nis

@ThePrimeagen When you try and build the 'OS' and the 'Apps', the OS starts to suffer. Focus on building great models and agents.

English

0

194

ThePrimeagen@ThePrimeagen·11 Nis

I think I could help Anthropic Mythos fix opus, no mistakes

English

132

121

4.6K

159.1K

tk | Obsidian×AIエージェントで無双する大学生@pkm_tk111·10 Nis

Agent to Agentがこんな視覚的に簡単に。。最高やな....！

日本語

3

12

250

24.4K

Zan@Sodanzen·11 Nis

@pkm_tk111 How did you link them?

English

0

55

Zan@Sodanzen·11 Nis

@TeeDevh codex way more reliable atm

English

0

66

Vu.@TeeDevh·11 Nis

Honestly stuck between 4 options: 3 × $20 Codex 3 × $20 ClaudeCode 1 × $100 Codex 1 × $100 ClaudeCode What would you pick? 🤔

English

213

5

379

93.5K

Zan@Sodanzen·10 Nis

@RedCollie1 @realDavidBauer Why don't you two work on it together - I bring emotional support

English

0

5

Red Collie (Dr. Horace Drew) scientist/inventor@RedCollie1·10 Nis

@realDavidBauer you should try to build it

English

2

0

3

50

Red Collie (Dr. Horace Drew) scientist/inventor@RedCollie1·10 Nis

Now I have found a "spin / counter-spin" interaction for my new UFO model, which is flat, quiet, and matches exactly, how the inner spinning magnet is supposed to move, relative to an outer, counter-spinning flywheel of 4 magnets. The whole device is driven by 3 central wire coils with U-V-W power, and 6 outer wire coils with U-V-W-U-V-W power. The inner spinning magnet is attracted to those outer 4 ring magnets, and TRIES to make them move upward, as both rotors spin and counter-spin at a relative 2 x 30 Hz. I will attempt to measure precise forces soon. 🛸 Never studied before. Based on plans supplied by friendly aliens. You have been lied to big-time.

Red Collie (Dr. Horace Drew) scientist/inventor tweet media

English

5

8

72

2.6K

Zan retweetledi

Anthony Kroeger@kr0der·10 Nis

GPT 5.4 in Codex really feels like you never need to worry about compaction long running chats feel perfectly fine, they've worked some magic here

English

47

18

894

29.2K

Zan@Sodanzen·10 Nis

@romainhuet Awesome, can you also look into when weekly limit is reached why additional credits purchased cant be used. Seems counter intuitive, I bought additional credits = weekly limit does not apply while unused credits exist

English

0

72

Romain Huet@romainhuet·9 Nis

Many of you have been asking for this: say hello to the $100 Codex Pro plan! It comes with very generous limits. Go build something ambitious!

OpenAI@OpenAI

We’re updating our ChatGPT Pro and Plus subscriptions to better support the growing use of Codex. We’re introducing a new $100/month Pro tier. This new tier offers 5x more Codex usage than Plus and is best for longer, high-effort Codex sessions. In ChatGPT, this new Pro tier still offers access to all Pro features, including the exclusive Pro model and unlimited access to Instant and Thinking models. To celebrate the launch, we’re increasing Codex usage for a limited time through May 31st so that Pro $100 subscribers get up to 10x usage of ChatGPT Plus on Codex to build your most ambitious ideas.

English

43

11

428

20K

Zan@Sodanzen·10 Nis

@OpenAI Can you fix the issue where weekly limit shouldn't stop you from continuing if there additional purchased credits that remain unused.

English

0

479

OpenAI@OpenAI·9 Nis

Our existing $200 Pro tier still remains our highest usage option. And as a thank you to our existing Pro users on the $200 tier, we’re extending our 2x Codex usage promo (until May 31st) and we’ve reset your Codex rate limits (yes, again).

OpenAI@OpenAI

We’re updating our ChatGPT Pro and Plus subscriptions to better support the growing use of Codex. We’re introducing a new $100/month Pro tier. This new tier offers 5x more Codex usage than Plus and is best for longer, high-effort Codex sessions. In ChatGPT, this new Pro tier still offers access to all Pro features, including the exclusive Pro model and unlimited access to Instant and Thinking models. To celebrate the launch, we’re increasing Codex usage for a limited time through May 31st so that Pro $100 subscribers get up to 10x usage of ChatGPT Plus on Codex to build your most ambitious ideas.

English

373

299

5.3K

829.2K

Zan@Sodanzen·10 Nis

@nickbaumann_ /fork current chat can be useful on working with multiple codex instances while working on parallel codebase features

English

0

1

24

Nick@nickbaumann_·9 Nis

Trying to find more Codex power-user workflows What are you doing with it now that feels obvious to you now but would’ve surprised you a month ago?

English

103

11

350

56K

Zan@Sodanzen·10 Nis

@sama Can you also fix the issue when weekly limit is reached and when additional credits are then purchased - the weekly limit shouldn't stop me if new purchased credits sit there unused. @OpenAI

English

0

16

Sam Altman@sama·9 Nis

It is very nice to see Codex getting so much love. We are launching a $100 ChatGPT Pro tier by very popular demand.

English

1.6K

427

11.7K

1.1M

Zan@Sodanzen·9 Nis

@mc_anthropic You should stick to doing what you do best, build strong models and agents, leave the application layer to others. What you are trying to do is same as if apple built the iPhone and then also tried to sell you all the apps that come with it.

English

0

1

333

Michael Cohen@_hi_mc·8 Nis

Hi, I'm Michael, an engineer working on Anthropic's API team. I'm really excited to finally be able to talk about Claude Managed Agents, a suite of APIs and developer tooling we've been working on for the past few months.