Rainer Dechet

Frontend & AI Agent Engineer @appamass | Agent Development Kit (ADK) AI Agents, React Native/Expo Apps & React/Vite Web Products

[le.hl @0xleegenz]

POV: Developers going to a job interview after AI can build itself

[diva @divaagurlxw]

As an AI Engineer. Please learn

>Harness engineering, not just prompt engineering

>Context engineering, not just long prompts

>Prompt caching vs. semantic caching tradeoffs

>KV cache management, eviction, reuse, and memory pressure at scale

>Prefill vs. decode latency and why they optimize differently

>Continuous batching, paged attention, and throughput optimization

>Speculative decoding vs. quantization vs. distillation tradeoffs

>INT8, INT4, FP8, AWQ, GPTQ, and when quantization hurts quality

>Structured output failures, schema validation, repair loops, and fallback chains

>Function calling reliability, tool contracts, argument validation, and idempotency

>Agent guardrails, loop budgets, tool budgets, and termination conditions

>Model routing, graceful fallback logic, and degraded-mode UX

>RAG architecture: chunking, embeddings, hybrid search, reranking, and freshness

>Retrieval evals: recall, precision, grounding, attribution, and citation quality

>Evals: golden sets, regression tests, adversarial tests, LLM-as-judge, and human evals

>LLM observability as a first-class discipline: traces, spans, tokens, latency, errors, and drift

>Cost attribution per feature, workflow, tenant, and user journey not just per model

>Safety engineering: prompt injection defense, data leakage prevention, and permission boundaries

>Multi-tenant isolation, cache safety, and cross-user context contamination prevention

>Fine-tuning vs. in-context learning vs. RAG vs. distillation and when each is the wrong tool

>Latency, quality, cost, and reliability tradeoffs across the full inference stack

>Production failure modes: hallucinated tool calls, malformed JSON, stale retrieval, runaway agents, and silent eval regressions

[Codez @0xCodez]

Claude Code creator:

"I don't prompt Claude anymore. I write loops - and the loops do the work. My job is to write loops."

in 30 minutes Boris reveals his actual daily Claude Code setup.

Claude Code + loops + dynamic workflow

Worth more than a $500 vibe-coding course

[Cory House @housecor]

AI took my programming job in 2025.

(It took your job too, though you may not realize it yet)

My new job? Solving software problems using agents.

(It’s your new job too)

[AVB @neural_avb]

Wake up babe THE Claude Code guy dropped a free masterclass on harness engineering

[SHILL HOUSE @shillhousecom]

Infinite money glitch

[Juan @XaLaRa_Se_Lew]

🤣🤣🤣🤣

[Aaron Grider @aarongrider]

I’m hiring exceptional software engineers for my team at @SpaceX.

We are a small team based in Redmond, WA (onsite) that owns key parts of the @Starlink user experience: https://t.co/HkjqT1Kf1w, the mobile app, customer support, AI integrations. No PMs. No designers. You ship from day one to millions of customers.

If this sounds interesting, DM me something impressive you’ve built.

[NO CONTEXT HUMANS @HumansNoContext]

Don’t blame technology

[𝐑.𝐎.𝐊 👑 @r0ktech]

someone who enjoys coding 😂

[Massimo @Rainmaker1973]

Multitasking vs focus

[Rainer Dechet @rainerdechet]

Upper Management Meeting. https://t.co/w1Rxp6zLmf

[Pablo Fredrikson @PeladoNerd]

https://t.co/zfFpPnJbdr

[Rainer Dechet @rainerdechet]

Build long-running agents with Google’s Agentic Stack | The Agent Factory https://t.co/VBj7wtSDKk via @YouTube

[Programmer Humor @PR0GRAMMERHUM0R]

broUsedAllHisThinkingTokens

[sudox @kmcnam1]

jfc....

[Jamon @jamonholmgren]

Agentic coding tip

Pay down tech debt immediately

With agents, there should be no such thing as “tech debt”. An agent should simply pay down every bit of tech debt before presenting you with the “finished work”. Unlike humans, agent time is not very valuable; it can and should continue to work on something until it’s done, and shouldn’t make concessions assuming human constraints.

If an agent tells you that it’s “leaving something for later”, tell it to go finish it first before saying it’s done.

Example prompt (best if it is in your docs):

```
Do not leave any tech debt behind. If you have taken any shortcuts, go back and do them right. This is a hard acceptance criteria that must be completed.
```

[SHILL HOUSE @shillhousecom]

Companies nowadays be like :