Alex

Engineer by trade. Curious by nature. Building systems, breaking assumptions, learning how humans and machines think. Building DATAMIMIC and ArchKeel

[Alex @Ake2l]

@Corporate_CJP @sherifgjini 🙌🏻😊

[Alex @Ake2l]

@sherifgjini I prefer a tool and model agnostic approach, so far , I am pretty satisfied and it's working well

[Alex @Ake2l]

Everyone's posting fancy agent graphics. Here's ours, built from git history and agent logs.

DATAMIMIC CE refactoring: 175 commits, 1,886 file changes, 23 → 9 package groups.

80 sub-agents in the last 5 days. 55 of them did nothing but verify.

Most agents checked. Few wrote.

[Alex @Ake2l]

@ohdearlordylord @grok Can you break this down for someone new to the topic?

What exactly am I looking at? How was this graphic created, and what data or assumptions drive it?

What are the main benefits, limitations, and trade-offs?

Keep it simple, practical, and objective. No hype.

[Alex @Ake2l]

@coryalthoff Everywhere obviously... Just vibe coded another trading platform with super fancy gif execute automatic trading ... Making 6.846.467,09 💲 per day with magic data and beautiful visualization, only took me 2 h and the wish for getting rich , super fast

[Alex @Ake2l]

@Saanvi_dhillon I guess it's a good editor , use it , but most projects have python stack and I still like the Jetbrain products , maybe it's i am a bit nostalgic, like to feel close to the code 😁

[Alex @Ake2l]

@0xPrajwal_ Then let's us all give it a try and see how good it is in real ... But I heard not available for public 😉

[Alex @Ake2l]

@sherifgjini I feel ai is expensive.. and it is si now 😉

[Alex @Ake2l]

@anah_sahh Is it ? ... do you outsource thinking to the AI ? Or do you use it as sparing partner and think accelerator ?

[Alex @Ake2l]

@SidharthVijay_ When you say Astra ... but the old one ;) ... i would be astra , otherwise i guess opus 5.5 is the better choice

[Alex @Ake2l]

@AdityaJhajhar12 I like the Astra light a lot 🤣 ... Looks like a cool way of horse dancing

[Alex @Ake2l]

@Taniyatweets_ First prompt: "Oh my God, this is magic." 60 billion tokens and 3 weeks of real data and real use cases later: the solution finally becomes useful.

[Alex @Ake2l]

@YashHustle_22 Vibe coding was driving fast to nowhere. Next wave: the navigation system. Architecture, tests, checks.

[Alex @Ake2l]

@jpschroeder First prompt is always most impressive ... but the outcome mostly only look good ... the real work and cost of token is coming after

[Alex @Ake2l]

@rafaelobitten @OpenAIDevs @thsottiaux Yes , sometimes i also get the message ... my agent session even stopped after 3 failing retries ... but luckily this rarely happens

[Alex @Ake2l]

We say we want people to take responsibility.

Then we build organizations where taking responsibility is riskier than doing nothing.

Why are we surprised when nobody takes ownership?

[Alex @Ake2l]

@thsottiaux @TimJayas 😂

[Alex @Ake2l]

@ivanainai So beautiful ... The chatgpt version, lovely

[Alex @Ake2l]

We spent three weeks refactoring DATAMIMIC CE with AI agents. The hard part was knowing whether we could trust the result.
I wrote up what held up, where our checks failed, and how we kept architecture in a versioned contract.
https://t.co/bzsme7PuHG