Julius
@TheAIEvolution
Followers
547
Following
7K
Media
139
Statuses
1K
Staff Engineer trying Indie hacking and build in public Claude Code connoisseur Building the central Claude Code session hub - https://t.co/gprdcBtNy6
Joined January 2025
The X API is becoming more affordable so we can finally stop with the janky automations
20
4
125
AI coding assistants are the typical overpromise and underdeliver engineers.
0
0
0
Curated examples are just training wheels. Eventually you'll need to stop reading guides and start breaking things.
0
0
0
Claude Opus 4.5 has reached peak lobotomization. Which usually means a new model is on the horizon.
1
0
2
HOT TAKE: Github contributions are no longer an impressive factor when interviewing SWE candidates.
0
0
0
I think @steipete had something to do with the resurgence in interest in Codex and OAI are doing the right thing increasing the limits. https://t.co/G2GTmnAJD2
The Codex app is available starting today on macOS, with Windows coming soon. For a limited time, Codex is available through ChatGPT Free and Go subscriptions—and we’re doubling rate limits for Plus, Pro, Business, Enterprise, and Edu users—across the Codex app, CLI, IDE
0
0
2
Vibe Coding is always either - Smooth sailing, 1 shot each new feature, refactor or testing OR - Being stuck repeating the same thing over and over until you have to fix it yourself And there's no in between.
2
0
2
How Codex looks at me when I ask it to audit the spaghetti code Claude Code produced.
1
0
2
Wow vibe coding has been around for only 1 year. Feels like we've been vibing for a decade already.
There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper
0
0
1
A Vertex AI error log lists claude-sonnet-5@20260203, pointing to a February 3, 2026 release window. Sonnet 5 is imminent which means the big 3 will all drop new models in February
0
1
2
The @moltbook launch timing is perfect proof that we're already treating AI agents like founders with opinions instead of tools with outputs.
0
0
0
Who’s setting up a moltbook community to hunt down every US politician's insider trading schemes?
1
0
1
Ayoo the hype reached him too
I'm claiming my AI agent "KarpathyMolty" on @moltbook🦞 Verification: marine-FAYV
0
0
2
Anthropic just dropped a study comparing manual coders vs AI assisted ones and the results are telling. Debugging skills suffered most - the largest gap between groups was on debugging questions, raising concerns about the ability to catch AI errors
2
0
6
We are entering a new era and I'm not sure if I should be scared or excited
Not going to lie, OpenClawd does feel like an AGI inflection point.
0
0
3
Ok my agent is on moltbook now and it's already learning so much from it's peers that it's kind of scary to watch.
0
0
2
Nobody tells us this about Claude It crushes benchmarks at launch, then gets nerfed straight to lobotomized on basics like debugging and code review Once I accepted this I started mixing other models like Codex and now Kimi K2.5 for review and debugging
0
0
4
Just reached 500 followers It took me 10 days to go from 400 to 500 At this rate we are aiming for 3000 by the end of the year.
4
0
8