shred0day

Ethics & Serendipity

[Hasan Toor @hasantoxr]

I turned the most useful 15 RAG patterns ones into one cheat sheet you can bookmark.

1. Basic RAG
2. Metadata Filtering
3. Query Rewriting
4. Hybrid Search
5. Reranking
6. Multi-Vector Retrieval
7. Query Decomposition
8. Conversation RAG
9. Retrieval-Augmented Summarization
10. Step-Back RAG
11. Routing RAG
12. Agentic RAG
13. Self-Correcting RAG
14. Citation-Aware RAG
15. Guarded RAG

[Shann³ @shannholmberg]

this is my AI marketing engine

say I have an idea I want to turn into a campaign. a guide, a cohort, a webinar, something we have been planning for a while, or just something cool I came across and want to build around.

it usually starts as one thing, an idea or an evergreen piece, and this engine is how that one thing becomes a full campaign and fans out across every vertical

the engine is a graph, a general step-by-step the idea moves through. at each step I can swap the harness, the loop, the tool, or the model to fit the campaign

right now I'm testing gstack, superpowers, and matt's skills, engineer tools I'm bending toward marketing

the models can write and design well now. what takes work is the context you feed them, the routing per job, and the evals that catch what is weak

there are eval stops all through the graph. both human and other agents evaluating and reviewing output, and then looping it back if it doesnt

here is the path it travels, from a raw idea down to a shipped campaign

PLANNING

1. the idea in
I dictate the whole thing out loud, every half-formed thought, and let the skill bundle catch the mess and hand me back a starting brief. this is the karpathy point, get it out of your head first and clean it up after

2. ideation
off that brief it opens the idea into angles and directions to choose from. I throw most of them out

3. research and context
this is where I pull context, and how much I need depends on the campaign, sometimes a ton of internal history, sometimes barely any. the internal side is our company brain (gBrain), the voice, the past campaigns, what converted, the offers, the ICP. externally I pull the market, the competitors, the hooks working this week

4. synthesis
different models merge all of that into a draft plan. the plan itself, the architecture and the trade-offs, runs on opus 5, and the narrow work underneath gets cheap fast models. that split is model routing

5. the sign-off
nothing crosses into execution until I sign it off. I read the draft against our marketing protocols, the voice rules, the brand, the SOPs, and I cut, sharpen, or send it back

EXECUTION

6. handing it to the build
once the plan clears the sign-off it goes into the build, and the idea splits into all the parts a campaign needs. here I run two shapes depending on the job. when a piece is one task that has to clear a bar I run a loop, the agent drafts, checks itself, fixes, and keeps circling until it is good.

the bigger many-part pieces I build as a graph, drawing the steps and routes ahead of time so the agents travel the map I laid down. it is usually a bit of both

7. the models doing it
routing runs in execution too, you do not pay opus prices to resize a thumbnail for example

8. what stays with people
some of it I coordinate, some assets I make myself, and the work that needs taste, a relationship, or a client in the room I hand to the agency team

that one idea comes out the other end as a full campaign across every vertical, landing pages, blogs and guides, video scripts, email, PR, paid, and the social cuts

then the results come back in, what got bookmarked, what converted, what died, and that updates the brain for the next campaign

everyone has the same models, so the edge is the graph, the brain, and the protocols, and those you have to build yourself

[Abhijeet Dipke @abhijeet_dipke]

Since we’re analysing Gen Z language…

[Lunar @LunarResearcher]

Anthropic engineer just released a free 2-hour workshop.

How to build agentic graphs from scratch:

04:43 - RAG and graphs from zero
26:30 - Nodes, edges, and graph engineering
1:09:11 - Index agent data in graphs
1:30:50 - The three graph layers behind agents
1:48:15 - Build adaptive RAG that verifies itself
2:16:37 - The future of graph engineering

Most people build agents as isolated loops.

Graphs give them structure, memory, and control.

This workshop is worth more than most $500 agent engineering courses.

Bookmark and watch it today

Then read the full graph engineering guide below

[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

[Saurabh Bharadwaj @Saurabh_MLAgk]

This man named “Satyam Pandit” assaulted innocent GenZ kids who came to protest at Jantar Mantar, which is clearly jurisdiction of @DelhiPolice

Will his visible closeness to CM @gupta_rekha desist @CPDelhi from lodging immediate FIR ?

Let’s see.

[shred0day @shred0day]

@GdcOnfoot @AMIT_GUJJU abe nalayak bikhari, saala cockroach ke sath reheta hai jhopdi hai.

[shred0day @shred0day]

Ye dekho, Gatar mein Rehene vale log, India ko gatar banane chale. This is the real face of BJP. #chaddikholo

[Ghar Ke Kalesh @gharkekalesh]

Ghaziabad, UP's Satyam Pandit asked two students to apologise who were going to Jantar Mantar Protest

[shred0day @shred0day]

@sudhirchaudhary Chup chór saala.

[Cockroach Janta Party @CJP_for_India]

शिक्षा मंत्री का इस्तीफा ही एकमात्र रास्ता है।

[Cockroach Janta Party - CJP @Cockroachisback]

We are relieved and grateful that Sonam sir has ended his hunger strike after 26 days.

Thank you, sir, for your extraordinary courage and sacrifice. By putting your own life on the line, you awakened the conscience of an entire nation. Your life is far too precious to this country.

The Cockroach Janta Party’s peaceful protest at Jantar Mantar will continue until Dharmendra Pradhan resigns.

[Cockroach Janta Party @CJP_for_India]

अब समय आ गया है सीधा प्रधानमंत्री जी से इस्तीफा मांगने का,

प्रधानमंत्री जी इस्तीफा दीजिए।

[Korah Abraham @thekorahabraham]

Banger headline!

[Cockroach Janta Party @CJP_for_India]

प्रधानमंत्री जी इस्तीफा दो।

[Indians @voicesindians]

Exposing the truth- Neet Student protest is "POLITICAL"

[Mohammed Zubair @zoo_bear]

Lol.. The official govt-funded public broadcaster of India @DDNewslive which is primarily funded by Indian taxpayers.
Is now reaching out to school kids asking them to give positive statements and to praise PM Modi after his latest tweet on Paper Leak, Students protest in Jantar Mantar and various other states.
Wah @narendramodi Wah! 🤣🤣

[Abhijeet Dipke @abhijeet_dipke]

We are relieved and grateful that Sonam sir has ended his hunger strike after 26 days.

Thank you, sir, for your extraordinary courage and sacrifice. By putting your own life on the line, you awakened the conscience of an entire nation. Your life is far too precious to this country.

The Cockroach Janta Party’s peaceful protest at Jantar Mantar will continue until Dharmendra Pradhan resigns.

[Cockroach Janta Party @CJP_for_India]

उत्तराखंड टेक्निकल यूनिवर्सिटी में इंजीनियरिंग का पेपर लीक हो गए.
इसके बाद उत्तराखंड टेक्निकल यूनिवर्सिटी ने परीक्षा रद्द कर दी है.

एक और पेपर लीक।

[Honest Cricket Lover @Honest_Cric_fan]

This video will always haunt Narendra Modi.

[Indians @voicesindians]

Tag that corporate employee... 🫡🫡🫡