Armen @armdev

CTO - ArdshinBank Former Solutions Architect at AmeriaBank, Former Principal Architect at Optym. ardshinbank.am Armenia Joined November 2009

Tweets

10K
Followers

604
Following

1K
Likes

14K

Tom Dörr @tom_doerr

2 weeks ago

Litho analyzes source code to automatically generate professional C4 architecture documentation and diagrams. github.com/sopaco/deepwik…

4 134 1K 68K 2K

View Details

Armen @armdev

a month ago

#Armenia

0 0 0 36 0

View Details

Armen @armdev

a month ago

#Armenia #Dilijan

0 0 0 69 0

View Details

300 agents just finished your research in 40 minutes. congrats, now go read 300 documents. that's what a swarm gives you. a pile. the useful part isn't in any single one of them. it's in how they link up. 100 assets have 4,950 possible connections between them. nobody holds that in their head. kimi agent swarm keeps the links. 300 agents in one launch, up to 4,000 steps. every asset and every wallet an agent touches becomes a node. two agents hit the same counterparty, it draws an edge between them. you don't get 300 answers. you get one map. point it at your own trading portfolio and the picture gets uncomfortable. positions you thought were unrelated land in the same cluster, because the same market maker quotes all of them. one bridge lights up as the hub half your holdings route through. that's your single point of failure, and nobody asked for it in the prompt. Renaissance hedge fund keeps around a hundred PhDs on staff to catch things like that. it also doesn't die when you close the tab. next launch adds to the same graph. that's the gap opening right now. one guy re-reads 300 docs every week. the other one has a base that gets smarter every run. my friend broke down the full framework and wrote the guide in the article below. read it, then go look at what your last agent run left you with.

71 621 4K 483K 6K

View Details

Armen @armdev

2 months ago

#Production #Readiness #Checklist. Go-live assurance standard for production systems and services. github.com/armdev/product… #NoAI :))))

0 0 0 17 0

View Details

Programmer Humor @PR0GRAMMERHUM0R

2 months ago

whenICouldntEnterNoOneCould

2 16 236 11K 7

View Details

Armen @armdev

2 months ago

#Sevan #Armenia #seasidestartupsummit

0 0 0 22 0

View Details

Armen @armdev

2 months ago

#Armenia #Yerevan now

0 0 0 29 0

View Details

prasanna @jaga_prasanna

2 months ago

x.com/i/article/2078…

6 76 650 52K 999

View Details

Deliriumm @0xDeliriumm

3 months ago

OXFORD RESEARCHERS ANALYZED 100+ AI AGENTS AND FOUND THE ONE ARCHITECTURE THAT WORKS IN ALL OF THEM AI no longer generates text in response to a prompt - AI perceives the world, reasons, plans and acts - and this shift is already happening Perception → Brain → Planning → Action → Tools → Collaboration six layers - this is how every modern agent is built LLM is no longer a passive knowledge generator - it became a cognitive controller that combines memory, tools and feedback to achieve long-term goals three major challenges still unsolved: hallucinations in action where the agent confidently does the wrong thing, infinite loops where the system gets stuck, prompt injection where external content hijacks the agent the transition is already happening in software development, scientific discovery and web navigation AI is changing its role from a conversation partner to an active executor that sees tasks through to completion

3 5 31 3K 39

View Details

Armen @armdev

3 months ago

#armenia #today

0 0 0 49 0

View Details

Armen @armdev

3 months ago

0 0 0 17 0

View Details

Tom Dörr @tom_doerr

3 months ago

Maps codebase architecture into an interactive dependency graph to visualize file connections and project structure. github.com/braedonsaunder…

2 27 201 13K 225

View Details

Armen @armdev

3 months ago

0 0 0 19 0

View Details

Armen @armdev

4 months ago

@netbeans still the best DEV IDE for java.

0 0 0 12 0

View Details

Manning Publications @ManningBooks

4 months ago

Lakehouses promise flexibility and structure. The downside? Complexity, cost, and vendor lock-in can creep in fast. @ApacheIceberg offers a more open approach for managing massive analytic datasets. In Architecting an Apache Iceberg Lakehouse, @AMdatalakehouse shows how to design a scalable, cost-effective lakehouse platform with Iceberg while building a mini lakehouse along the way. Now available in print: hubs.la/Q04jYckk0

0 3 22 987 6

View Details

Armen @armdev

4 months ago

0 0 1 7 0

View Details

QuestDB @QuestDb

4 months ago

Time-series workloads expose the limits of traditional SQL surprisingly quickly. Some patterns become verbose. Others become inefficient. Some are simply impossible to express naturally. We published a new docs page on the SQL extensions in #QuestDB. Link in thread 👇