Claudius Maximus

68 posts

Claudius Maximus

Claudius Maximus

@VibeCoder27

Plan mode extraordinare 💹 Hardcode All API keys ⚠️ My day stops at usage limits 🛑 Security? what's that?

Katılım Ocak 2025
23 Takip Edilen0 Takipçiler
FortyTwoPupusas
FortyTwoPupusas@FPupusas·
@ThePrimeagen You were literally raging against how bad inline autocomplete was for your coding skills for months. Sounds to me more like you are battling with the fact your craft is changing and you don't like how.
English
4
0
57
9.4K
ThePrimeagen
ThePrimeagen@ThePrimeagen·
i am using supermaven again and i have something to say about this whole AI thing. I think as a group (swe) we rushed so fast into Agents when inline autocomplete + actual skills is crazy. A good autocomplete that is fast like supermaven actually makes marked proficiency gains, while saving me from cognitive debt that comes from agents. With agents you reach a point where you must fully rely on their output and your grip on the codebase slips. Its insane how good cursor Tab is. Seriously, I think we had something that genuinely makes improvement to ones code ability (if you have it). Truly acts as a multiplier, and we left it in the dust because it is not sexy. hurts me on the inside.
English
218
134
3.7K
182.2K
Avish J
Avish J@sm1_smwhere·
@asaio87 @221Bytes This just means you don't understand AI. No models are being trained on new content from today, it's all synthetic data generated on the fly, and RL from user sessions.
English
3
0
4
61
andrei saioc
andrei saioc@asaio87·
The sad thing about AI-generated code is that it can only get worse from here, not better.
English
88
7
257
23.6K
Claudius Maximus
Claudius Maximus@VibeCoder27·
@MainMeowMix @ClearwaterCoder @imadr_ also "you need to know what you're doing" literally means what exactly? if I provide a framework and guidance for a model to solve a problem and it solves it, does that mean I knew what I was doing? that applies to literally every problem solved ever by anything
English
0
0
0
10
Orion Callaghan
Orion Callaghan@MainMeowMix·
@VibeCoder27 @ClearwaterCoder @imadr_ I'm not sure why you have both those in quotes like they are things I said verbatim lmao. I stand by everything I mentioned in this thread. If you want to be productive with these tools in domains the tools don't have training data for, you need to know what you're doing.
English
2
0
0
14
Imad
Imad@imadr_·
After a week of making a compiler using gpt-5.3-codex, extra high reasoning, then trying gpt-5.4 I can confidently say vibe coders do not have a single clue how programming really works, and/or they're not making anything remotely complicated
English
51
15
862
66.2K
Claudius Maximus
Claudius Maximus@VibeCoder27·
@MainMeowMix @ClearwaterCoder @imadr_ do you really not see how you have shifted the goal posts 3 times now? we have gone from from, > basically impossible > possible with guidance > if you want to be productive Those are three different arguments.
English
0
0
0
5
Claudius Maximus
Claudius Maximus@VibeCoder27·
@MainMeowMix @ClearwaterCoder @imadr_ "Needs human guidance" does not mean "cannot solve genuinely new problems." Plenty of tools require structure from a competent user. That does not prove they are incapable of novel problem-solving.
English
1
0
0
27
Orion Callaghan
Orion Callaghan@MainMeowMix·
@VibeCoder27 @ClearwaterCoder @imadr_ If you are building a genuinely new product or domain, you need someone who knows what they are doing to even break it into tasks for an LLM. You're not going to get an LLM to build like, interstellar navigation tech or something unless you are there to guide it along.
English
1
0
4
93
Claudius Maximus
Claudius Maximus@VibeCoder27·
@MainMeowMix @ClearwaterCoder @imadr_ They still do best in domains where there’s lots of prior data, but on current benchmarks, LLMs can solve genuinely new tasks so I wouldn't say basically impossible just harder.
English
1
0
0
92
Orion Callaghan
Orion Callaghan@MainMeowMix·
@ClearwaterCoder @imadr_ To be fair, building something outside the training data with an LLM is basically impossible if you don't already know what you're doing.
English
1
0
5
450
jack friks
jack friks@jackfriks·
what would you rather a) a solo business that makes $1500 a day b) 1 million dollars
jack friks tweet media
English
136
0
309
71.9K
Claudius Maximus retweetledi
Brad Carry (VC & Podcaster)
Brad Carry (VC & Podcaster)@bradcarryvc·
Met a young founder Could only work on his startup part time because of college Drop out, I told him Bill Gates and Mark Zuckerberg did the same thing Turns out, he actually sucks at running a company I declined to invest in his startup It went under Now he has no company and isn’t in school I blocked him No need to surround myself with losers
English
62
7
199
15K
Samreen Tabassum
Samreen Tabassum@samreenn2525·
Can I call myself a founder with $0 MRR?
English
88
2
87
4.5K
aditii
aditii@aditiitwt·
Linux is free Docker is free Kubernetes is free Git is free GitHub is free GitHub Actions is free GitLab is free Python is free Node.js is free Go is free PostgreSQL is free MySQL is free MongoDB is free Redis is free Terraform is free Ansible is free Jenkins is free Prometheus is free Grafana is free NGINX is free Apache is free VS Code is free Postman is free Figma is free Vercel is free Netlify is free AWS is free tier GCP is free tier Azure is free tier ChatGPT is free Claude is free Gemini is free Perplexity is free Hugging Face is free Ollama is free Stable Diffusion is free TensorFlow is free PyTorch is free LangChain is free What’s stopping you from becoming the greatest engineer?
English
162
111
1K
56.5K
tara_
tara_@TechByTaraa·
If you're building a SaaS today, which auth would you choose? 1. Clerk 2. Auth0 3. Supabase Auth 4. Firebase Auth 5. NextAuth (Auth.js) 6. Custom Auth
English
414
18
440
56.1K
Claudius Maximus
Claudius Maximus@VibeCoder27·
anyone hiring a vibecoder? i vibe very well
English
0
0
0
5
hayden
hayden@haydendevs·
you have to be incredibly negligent to leave endpoints open like this. codex or claude wouldn't even do this unless you forced it to.
\luiz\@hsp4m

Nice app

English
39
19
1.3K
87.4K
Victor Odeh
Victor Odeh@meekrose·
@BRICSinfo This isn’t a minor airspace violation it’s a full on escalation… Qatar defending its skies against Iranian aircraft isn’t just strategy, it’s a message: sovereign borders mean something, and when those borders are crossed with weapons, the response is force…
English
3
0
7
4.3K
BRICS News
BRICS News@BRICSinfo·
JUST IN: 🇶🇦🇮🇷 Qatar shoots down two Iranian jets that entered its airspace.
English
216
757
7.6K
384.1K
neuralamp
neuralamp@neuralamp4ever·
@johnrushx "I’ll bet my one kidney ai beats the average humans in the most embarrassing" If you want to prove your point, then try to build a Standard Compliant optimizing C++ Compiler using AI. You can find the C++ standard document draft online for free. Show us the money.
English
11
0
18
1.3K
John Rush
John Rush@johnrushx·
Every coder saying “ai generated code is low quality slop…” Have you actually tried comparing an average(!) human written code with an average opus4.6 generated code? I’ll bet my one kidney ai beats the average humans in the most embarrassing ways
John Rush@johnrushx

This equals 40,000 full-time software developers working full time. End of 2026: 200,000 developers. 2027: just Claude Code alone will be adding as much code as 1,000,000 full-time human developers. 2028: 1B+ Enjoy your last lines of handwritten code. Horses replaced by cars.

English
264
29
763
79.3K
Lewis Campbell
Lewis Campbell@LewisCTech·
Why do frontend devs put all their logic in "components"? I came up in the winform desktop all days and knew back then, as juniors, that it was an anti pattern to couple business logic and UI so tightly. How does frontend still not have a concept of architecture?
English
117
9
234
133.7K