Doheeie

Lost between AI & crypto fr
I'm into what you're into🔥

글은 내 쪼대로😉

[Doheeie @doheeie]

MAJOR : #yapping #tugging

@MemeCore_ORG @MemeX_MRC20
@KaitoAI

[음머 @bestcow08]

https://t.co/cr7BV221Tm
이거 좋다
기초 심화 다있다

[Doheeie @doheeie]

@winneravgwin 하잉~

[Doheeie @doheeie]

GN해라

[Doheeie @doheeie]

@_meganpark 관심고맙ㅜ

[Doheeie @doheeie]

have you ever seen a Series H company? 👀

[Anthropic @AnthropicAI]

We've raised $65 billion in Series H funding at a $965 billion post-money valuation, led by @AltimeterCap, Dragoneer, @Greenoaks, and @sequoia.

This investment will help us advance our research and expand our capacity to meet growing demand for Claude.

[Doheeie @doheeie]

@alex_grankin @claudeai "you can trust it with more"

[Doheeie @doheeie]

@AnthropicAI @AltimeterCap @Greenoaks @sequoia Anyone still saying AI is a bubble?

[Doheeie @doheeie]

@malanghk1 젊은친구가 대단하네

[Doheeie @doheeie]

@malanghk1 개일찍일어나시네 ㅁㅊ

[Doheeie @doheeie]

8. Spend at least 20% of your time improving the process

Continuously refine instructions, workflows, evaluation methods, and automation systems. Focus on eliminating recurring mistakes while keeping the overall process simple and efficient.

[Doheeie @doheeie]

CEO of @NotionHQ hasn't written a single line of code since last summer.

The productivity advantage no longer comes from writing code.

It comes from designing systems where AI can work, execute, and deliver.

[Doheeie @doheeie]

7. Remove yourself from the execution loop

Avoid manually driving every step. Agents should execute tasks, validate results, and provide evidence of completion. Your role is oversight, not execution.

[Doheeie @doheeie]

6. Separate roles into specialized agents

Create dedicated agents for planning, implementation, review, testing, issue triage, and quality assurance. Build a workflow where each agent contributes its specialty.

[Doheeie @doheeie]

5. Set up adversarial reviews

Use independent reviewer agents to compare completed work against requirements, identify gaps, and challenge assumptions before work is considered complete.

[Doheeie @doheeie]

4. Spend your time writing planning documents

Instead of constantly monitoring the agent, invest in detailed planning documents. Good plans should be self-contained and include implementation details, interfaces, and end-to-end validation strategies.

[Doheeie @doheeie]

3. Maintain a persistent task queue

Always keep a backlog of well-defined tasks ready. Each task should include objectives, validation criteria, and evidence of completion so the agent never runs out of work.

[Doheeie @doheeie]

2. Keep sessions alive for days or weeks

Maintain long-running sessions so the agent can retain project context, conventions, architecture decisions, naming patterns, and coding styles over time.

[Doheeie @doheeie]

1. Increase the task scope

Don't break work into tiny pieces. Give the agent larger, outcome-oriented tasks that would normally take a senior engineer days or weeks to complete.

[Doheeie @doheeie]

@simonlast hasn't written a single line of code since last summer.

The productivity advantage no longer comes from writing code.

It comes from designing systems where AI can work, execute, and deliver.

[poi @poiddi]

레이스리더다가 차 퍼져서 63님 진짜 개빡치셧음……..