DanielA @PECULAR

Both a Daddy👶 & Zaddy💁‍ Building @workremits, built @joinsteward Ex @GetOurPass @BujetiHQ @paylidate #Otaku | #SoftwareEngineer | #EngineeringManager linkedin.com/in/danieladego… Remote Joined May 2009

Tweets

4K
Followers

1K
Following

2K
Likes

13K

DanielA @PECULAR

4 days ago

I'm having a huddle with my agents bro buzz is crazy @jack this is crazy...love it

0 0 0 44 0

View Details

DanielA @PECULAR

3 weeks ago

@patola58 Another liar/ignorant person he insinuated that the education should be free... because cost of education went up he is now providing that education to people as nelfund... Let's stop this lying

0 0 0 118 0

View Details

DanielA @PECULAR

4 weeks ago

@i_mika_el Jurisdiction is based on where the operation is done and the location of the responsibe party. This can be spread out or singular.

0 0 1 11 0

View Details

DanielA @PECULAR

4 weeks ago

Humanity is already expanding to: - AI agents performing work, - robots operating factories, - autonomous businesses, - settlements beyond Earth, - millions or billions of digital workers, Meaning the amount of "economic actors" would become much larger than the number of humans. Those actors will still need: - permissions, - ownership, - payments, - contracts, - accountability, - compliance with whatever jurisdiction governs them. @workremits we are building a layer that coordinates all of these☝️.

2 1 3 59 0

View Details

DanielA @PECULAR

4 weeks ago

This is the growing state of engineering instructions to LLM what next

0 0 0 45 0

View Details

DanielA @PECULAR

4 weeks ago

@SadiqMaunde Also he said the commissioner were Muslim then corrected himself and said north....let's not lie please

4 1 8 615 0

View Details

DanielA @PECULAR

4 weeks ago

@JoshofOwo @DavidsOffor @PeterObi He literally said it is in name... meaning it is a title that has no duties....please sir listen to context

3 0 1 177 0

View Details

DanielA @PECULAR

4 weeks ago

Accountability isn't assigned to the AI—it's assigned to the chain of responsibility. Every AI agent acts under a registered operator, every operator is bound to a legal entity within a jurisdiction, and every action is attributable, auditable, and policy-enforced. Geography becomes an implementation detail, not a blocker.

1 0 1 13 0

View Details

DanielA @PECULAR

4 weeks ago

For Bait Resistance you need to learn - Emotional Lag: Train a short delay between the stimulus (the insult) and your internal response. Stop treating the feeling as an urgent command. - Status Independence: This is built through repeated experiences of acting according to your own standards regardless of whether the other person approves. - Response Minimalisim: restate the original point return them to original or disengage. - Audience awareness without performance: remain factual and measured in those moments

0 0 0 11 0

View Details

DanielA @PECULAR

4 weeks ago

Practicing: - shame resilience - Bait Resilience from loved ones - Getting rid of Old Programming For Old Programming you know where you are going Re-Programme yourself as your goal need an evolved you. /1

1 0 0 52 0

View Details

Superlinear @superlinear_fm

4 weeks ago

Opus 5, Fable 5, and GPT-5.6 Sol already orchestrate agent graphs for you on their own. But should you let them? Or do you still need to design the loops and graphs yourself? We unpack the trade-offs in our latest episode.

Superlinear @superlinear_fm

4 weeks ago

7 19 101 42K 300

1 3 11 2K 5

View Details

Codez @0xCodez

4 weeks ago

Anthropic engineer just released a 2-hour workshop on "Graph Engineering" for agentic systems: “80% of our engineers are using self-improving loops. Now everyone is building agentic graphs.” • 00:00 - Introduction to RAG & Graphs • 06:39 - Core of "Graph Engineering" (state, nodes) • 14:29 - 3 feedback loops of Graph agents • 23:06 - Agent evaluation with Graphs • 36:29 - Agent cycles in graphs • 1:15:22 - Agentic RAG & agent context • 1:41:20 - Evaluation datasets based on Graphs This 2-hour workshop will replace 10 paid courses on agentic engineering. Watch it today, then learn how to become a Graph Engineer in the article below.

Codez @0xCodez

a month ago

x.com/i/article/2079…

118 769 4K 6.8M 14K

70 318 2K 400K 5K

View Details

Thariq @trq212

4 weeks ago

We removed ~80% of the Claude Code system prompt for our newest models, this is what we've learned about writing system prompts, skills and Claude.MDs for them. x.com/i/article/2080…

463 2K 16K 4.6M 33K

View Details

Anatoli Kopadze @AnatoliKopadze

4 weeks ago

Anthropic engineer: "You're not supposed to babysit the model. Put it in a graph, and it catches its own mistakes and runs a dozen tasks at once." In 25 minutes he breaks down exactly how Anthropic builds agents that run in parallel, check each other's work, and recover when one fails. Worth more than any paid course you'll find on building agents. Watch it, then read detailed guide on graph engineering below.

Anatoli Kopadze @AnatoliKopadze

4 weeks ago

x.com/i/article/2080…

78 420 3K 9.6M 13K

50 200 2K 415K 5K

View Details

Akshay 🚀 @akshay_pachaar

4 weeks ago

x.com/i/article/2081…

26 157 952 557K 2K

View Details

Superlinear @superlinear_fm

4 weeks ago

Understand the Loops and Graphs that Frontier Models Like Opus 5, Fable 5, and GPT-5.6 Use In our new episode: → How agent loops become graphs → Why focused subagents can perform better → Where the extra tokens go → When parallelism helps → When orchestration becomes expensive overhead → How to diagnose a run that gets slow, costly, or stuck You don’t need to design every graph yourself. But you should understand the graph your harness is already building. 00:00 Introduction 03:34 How the Agent Loop Works 06:18 Goal Loops and Autoresearch Loops 14:57 From Loops to Graphs 17:06 Sub-Agents: Benefits, Costs, and Context 21:18 The Research Fan-Out Graph 26:27 Multi-Model Agent Graphs 28:37 Asynchronous Implementation and Review 33:40 How to Design Agent Graphs 36:07 When the Harness Builds the Graph for You: Token Spend vs. Performance 38:38 Execution Traces: A Profiler for Agents 41:46 Final Takeaway

Christine Yip @christinetyip

4 weeks ago

x.com/i/article/2075…

2 4 33 11K 75

7 19 101 42K 300

View Details

Alex Kotliarskyi 🇺🇦 @alex_frantic

4 weeks ago

How to graph-max with Codex and 5.6 Sol: 1. Draw a graph (literally in any tool, even on paper) 2. Send it to Codex and say "write a code mode script that implements this workflow, run it with <your inputs>" There's no step 3, it just works. Seriously it's that simple.

43 134 2K 761K 3K

View Details

DanielA @PECULAR

4 weeks ago

@i_mika_el Exactly and that's what we are building for ensuring that even agents can be accountable

1 0 1 13 0

View Details

DanielA @PECULAR

4 weeks ago

So @workremits is closer to something like Jurisdiction-as-a-Service Every country is essentially an API. Nigeria() Kenya() Brazil() Japan() Each exposes different capabilities. - Different regulations. - Different tax engines. - Different payment rails. - Different employment rules. - Different customs. - Different restrictions. Our job is to normalize all of them. And we are already doing this in 12 African Countries

0 1 2 58 0

View Details

DanielA @PECULAR

4 weeks ago

@workremits we are building An abstraction layer over sovereign complexity. - Countries are the distributed systems. - Regulations are the programming language. - Businesses are the applications. - @workremits is the runtime. We are becoming the abstraction layer between businesses and jurisdictions.