degen.web

Science, Art and Tech Systems

[degen.web @validateweb3]

automation and SDLC

[How To Prompt @HowToPrompt__]

RAG is officially cooked.

IBM built a retriever that hallucinates 65x less than fine-tuned RAG systems.

Right now, every company is using Retrieval-Augmented Generation (RAG) to stop their AI from hallucinating.

The idea is to give the AI a private database to read so it doesn't make things up.

But there is a massive structural flaw.

Standard RAG blindly grabs documents based on vector similarity and forces the AI to read them. If the retriever pulls irrelevant garbage, the AI doesn't stop.

It just hallucinates with citations.

IBM just dropped a paper that changes the math entirely.

They built a new retrieval architecture that hallucinates 65x less than state-of-the-art fine-tuned RAG systems.

65x is the difference between a fun prototype and a production-grade enterprise system.

Instead of blindly dumping context into the model and hoping for the best, their system actively filters and validates the retrieved data before the generation step even begins.

It cuts out the noise. It forces absolute precision.

For businesses, this is the holy grail.

Zero hallucinations means zero liability. It means autonomous agents can finally be trusted with sensitive company data without a human babysitting every output.

[Danielle Langlois @DanielleLangWa]

Uh… guys?

[DamDam OF LAGOS LIFE 💯💐💚🤞🏿 @badoorichy]

NAH WHAT DID I JUST EXPERIENCE @Shalom_HeyEliy @LagosLifeApp see as I Dey excited like a 10 year old 😹!

HAD TO QUICKLY SHOW YOU GUYS!
GET IN JOOOOR!

#lagoslife

[degen.web @validateweb3]

@pipe_dev I can’t get API key

[The Liquid Metal Himself @iam_jerrymoses]

Now that we understand what money is, here’s a list of politicians with allegations of diversions of public funds and the amount-

1. Sadiya Umar Farouk - N729b
2. Sambo Dasuki - $2.1b (approx. N2.78 trillion)
3. Yahaya Bello - N190b
4. Saleh Mamman - N34b
5. Murtala Nyako - N29b
6. Darius Dickson Ishaku - N27b
7. Willie Obiano - N42b
8. Aminu Tambuwal - N189b
9. Hadi Sirika - N19b
10. Udom Emmanuel - N700b

[Eureka @eureka_seamless]

Super excited about this one 🥹
Mainland don do. Tomorrow, the Danfo Cross Bridge

Third Mainland Bridge, Makoko, Idumota, Marina, Lagos Island in Danfo Run

[Johan @liebert_2026]

making boring software fun is a bigger achievement than it sounds

[Akintola Steve @Akintola_steve]

There was a time I worked with a company where I implemented the entire auth module from the backend side of things. Everything that needed to be done was properly implemented.

The frontend guy consumed the endpoints, and we moved to testing.

All of a sudden, the QA guy kept complaining that whenever he logged in and refreshed the page, it took him straight back to the login page.

I was confused too. I went through my codebase over and over again, and everything was working as expected.

I then decided to check the frontend code and realised the guy was only storing the authentication state in memory and wasn't implementing a proper session restoration mechanism when the application reloads.

I told him to implement the session restoration flow properly and ensure the app verifies the user's session before redirecting to the login page.

He did it, we tested again, and the issue was gone.

Imagine if I hadn't checked the frontend code and we had kept going back and forth, blaming me, the backend guy.

[Suraj Sharma @suraj_sharma14]

As a Backend Engineer in the AI era, you must build these projects.

1.) High-Concurrency HTTP Server
Build: Go or Rust server handling 10k+ concurrent connections with graceful shutdown and backpressure.

Why: Concurrency architecture is the one thing AI cannot design for you.

2.) Multi-Tenant Hybrid Search Database
Build: Postgres with Row-Level Security + pgvector + BM25 hybrid ranking across isolated tenants.

Why: Structured data and semantic embeddings now share one query engine.

3.) Event-Sourced Order Pipeline
Build: Kafka or NATS pipeline with immutable events, dead-letter queues, exactly-once semantics.

Why: AI workloads are slow and async. The main thread must never block.

4.) Durable Onboarding Workflow
Build: 3-day Temporal workflow with checkpoints, retries and human approval steps.

Why: Background jobs are for emails. Durable execution is for multi-step agents.

5.) AI Gateway with Semantic Cache
Build: Proxy that caches similar prompts via embeddings, enforces token budgets and fails over to a cheaper model on 503s.

Why: The gateway protects your margins and your uptime from flaky, expensive LLM APIs.

6.) PII-Redacting Auth Middleware
Build: OAuth2/OIDC provider plus middleware that masks PII before logging and restricts AI agents to read-only DB roles.

Why: When agents can write to your database, a prompt injection is a data breach.

7.) Real-Time Streaming Dashboard
Build: SSE/WebSocket dashboard streaming LLM tokens and database updates simultaneously with backpressure.

Why: Time-To-First-Token and perceived latency are the new UX standards.

8.) Correlated Tracing Pipeline
Build: OpenTelemetry + Langfuse pipeline linking each HTTP request to the exact LLM prompt and DB query it triggered.

Why: You cannot debug a hallucination without replaying the exact context the model saw.

9.) Ephemeral Environment Provisioner
Build: Terraform or Pulumi scripts spinning up a complete isolated staging environment for every pull request.

Why: Manual deployments are a liability. Infrastructure must be version-controlled and reproducible.

10.) Queue-Based Autoscaler
Build: KEDA autoscaler spinning nodes up on Kafka queue depth and down when empty with spot-instance fallback.

Why: Backend engineers now own the cloud bill. Idle resources burn runway.

11.) Globally Distributed Rate Limiter
Build: Redis-backed distributed rate limiter that survives network partitions gracefully.

Why: Architecture must degrade gracefully not cascade into total outage.

12.) Chaos Engineering Suite
Build: Fault-injection harness (latency, replica kills, partitions) with SLO burn dashboards.

Why: Resiliency is proven under failure not in diagrams.

13.) Webhook Reconciliation Engine
Build: Idempotent event processor with exponential backoff, dead-letter queues and replay tooling.

Why: Real integrations fail constantly. Reconciliation is what makes them trustworthy.

14.) Cost-per-Request FinOps Dashboard
Build: Per-tenant, per-endpoint, per-LLM-call cost rollups with anomaly alerts.

Why: Visibility is control. You cannot optimize what you cannot attribute.

15.) Public Architecture Teardown
Build: 3 published deep-dives with system diagrams, ADRs and latency/cost benchmarks.

Why: Senior engineers are hired for their judgment not their syntax.

Systems that prove you can scale, secure & ship when agents touch your stack.

Most people watch tutorials. Builders ship systems.

Bookmark & Repost.

[Yehgha @yaygha]

Let a woman talk long enough and she will not only tell on herself, she will tell on you too.

[Okpe Onoja @iam_the_code]

Skill issue

https://t.co/qS4ktctWwR

Claude on auto👀

[Eureka @eureka_seamless]

@Lilllhannah holds #1 on Lagos Run with 569,110 points. Who fit collect am?

https://t.co/RQoubPBevS
#LagosRun

[degen.web @validateweb3]

Opus 5.5 went crazy on this one!
Screens re-rendered from the actual platform 🤯

#edTech

[Grant Miller @AIGuide_]

if you're confused about Jev this is 100% worth your time

in fact you should study it

[Rahul @sairahul1]

Mark Cuban on the next job wave:

"Software is dead because everything's gonna be customized to your unique utilization. Who's gonna do it for them..."

The answer is people who know how to fine-tune small LLMs on private data.

Not prompting. Not API wrappers.

Actual custom models trained on your business.

And almost nobody knows how to do it yet.

This is the complete guide ↓

Bookmark this. This is the one.

[Sunnyboss | UIUX @Sunnyboss__]

The Keke man see police for front, turn back Sharp 😂

[Akintola Steve @Akintola_steve]

Software Engineering Paths: Ultimate

Roadmaps (SAVE THIS)

4 tracks. One structure.
→ Backend
→ System Design
→ Frontend
→ AI Engineering

Learn to ship systems, not just write code.

[Max @Maxtheairbnbguy]

Beautifully furnished 2 bedroom apartment with a sex dungeon, BDSM kits, private cinema, bathub and a content house (Mr bowler) is available

Location📍Chevron, Lekki
180k

[Mustafa Ali @mustafa01ali]

https://t.co/PcXPOu2rAf

[Maester @Tekanomo_]

Day I finally understood Fourier Series and LaPlace Transforms (took me 3 hours of intense study), but something changed in my outlook forever.

Engineering Mathematics is quite simple, you just have to first get the principles.

Don't rush.
Don't let the symbols scare you.