Technical creator. Involved in everything AI, data, and tech
Joined March 2023
- Tweets1.5K
- Following206
- Followers84
- Likes14.3K
Your favorite tech creator retweeted
You're building an offline AI agent on a Raspberry Pi 5.
It needs to remember conversations after a restart and find old information when you ask in different words
What would you use for its memory?
A) JSON files
B) Bigger context window
C) Vector DB + embeddings
D) Fine-tuning
Your favorite tech creator retweeted
100K vectors on a Raspberry Pi 5.
Actian tested VectorAI DB on an 8GB Pi and got 4.98 ms p99 for top-5 search.
That's synthetic-vector retrieval.
Now I want to see how far this little board can go.
Full benchmark:
actian.com/blog/developer/bu…
Your favorite tech creator retweeted
One result surprised me while benchmarking web scraping tools.
Browserbase Fetch averaged 0.61s on TripAdvisor.
But all 100 requests returned 403.
Zenrows took longer but retrieved the page.
Speed means little if you can't access the data.
My benchmark:
zenrows.com/blog/best-browse…
Your favorite tech creator retweeted
I tested Zenrows Fetch vs Browserbase Fetch on 4 protected sites.
100 requests per target. 2 req/s.
Results:
• Zenrows: 100%
• Browserbase: 62.25%
These were default Fetch configurations for both tools, not full browser tests.
I documented the methodology:
zenrows.com/blog/best-browse…
Your favorite tech creator retweeted
Choosing a web search API for your AI agent?
Check:
1. Freshness
2. p95/p99 latency
3. Result quality
4. Coverage
5. Output format
6. Integration
7. Cost per answer
8. Reliability
This guide by Octen includes a scoring matrix. Save this post.
octen.ai/guides/how-to-choos…
Your favorite tech creator retweeted
Octen compared 8 embedding models for RAG.
On RTEB's 16 public datasets:
• Octen-Embedding-8B: 0.795
• Nemotron 3 Embed: 0.785
• Voyage-4-large: 0.762
But benchmark scores aren't a substitute for testing your data.
Full comparison:
octen.ai/versus/best-embeddi…
Your favorite tech creator retweeted
Before choosing an embedding model for RAG:
1. Collect real queries
2. Label relevant documents
3. Test 2–3 models
4. Compare NDCG@10
5. Check storage + re-embedding costs
Octen explains this approach while comparing 8 models:
octen.ai/versus/best-embeddi…
#rag #embeddings
Your favorite tech creator retweeted
You can search thousands of images using a text description.
The approach:
1. Encode images with CLIP
2. Store vectors + metadata
3. Encode the text query
4. Retrieve similar images
Actian built an offline defect-search demo with Python and VectorAI DB:
actian.com/blog/developer/bu…
Your favorite tech creator retweeted
What if your AI coding agent fixed a bug today, but then forgot the solution in the next session?
Came across a GPT-6 Astra experiment where they used Actian VectorAI DB as external memory to store and retrieve previously tested fixes across sessions.
It worked by:
-Search a vector DB for similar previous fixes
-Check if the old fix applies to the current code
-Save new fixes only after tests pass
They also tested it across 5 sessions and the agent successfully retrieved earlier fixes. I liked the idea of remembering tested fixes instead of the whole conversation.
I'm curious what others think about giving AI coding agents this kind of memory. Would it be useful in your workflow?
Your favorite tech creator retweeted
Zekeri throws a challenge to all the Abuja residents to disappoint Wike in 2027.
This is just the beginning, when the game finally starts, even Wike will plead for mercy.
How can one man say he will decide who wins elections in Federal Capital Territory?
Your favorite tech creator retweeted
Half the AI timeline right now: "You don't need a vector database."
The other half: "you'll regret not having one."
Both are right, depending on your workload.
So we built a tool that tells you which camp you're in.
Answer a few questions about your data, latency, filtering and deployment.
In 30 seconds, you'll know whether a flat file, keyword search or pgvector is enough, or whether you really need a vector database.
Sometimes the answer is no. We'll tell you that too.
bki.sh/RyqhiNN
Your favorite tech creator retweeted
Building an AI agent with memory?
Know these 4 types:
1. Working: current task
2. Episodic: past interactions
3. Semantic: learned facts
4. Procedural: workflows
Actian breaks down how they fit into production agent architectures:
dev.to/actiandev/what-you-ne…
Your favorite tech creator retweeted
Your AI agent has a web search tool but still answers current questions from memory?
Check the tool description.
"Search the web" isn't enough. Tell it WHEN to search: new releases, prices, versions, news, etc.
Octen explains this with a working LangChain example:
octen.ai/guides/how-to-add-l…
Your favorite tech creator retweeted
Before connecting a scraping API to your AI agent, check:
- Anti-bot reliability
- JS rendering
- JSON/Markdown output
- Request latency
- Cost per usable result
This article compared 4 popular APIs with an 800-request benchmark.
Good reference: zenrows.com/blog/best-web-sc…
Your favorite tech creator retweeted
A lot of “web-aware agents” are still:
fetch(url) → dump page into model → hope
Production gets messy fast.
JS, bot protection, noisy HTML, wrong page content, extraction formats.
This Mastra + Zenrows setup treats web access like infrastructure.
zenrows.com/blog/web-aware-t…
Your favorite tech creator retweeted
5 code review habits you should steal today for AI-generated PRs:
1. Read the ticket first
2. Review schemas/types before dependent code
3. Separate logic from formatting noise
4. Hunt assumptions, not syntax
5. Give agents a diff-size budget
CodeRabbit breaks it down here: coderabbit.ai/guides/code-re…
Your favorite tech creator retweeted
AI-assisted PRs are 2.6× larger on average in a recent benchmark data.
Once the diff gets huge, review quality drops fast.
A simple rule is to give coding agents a diff budget.
If the task crosses it, split the PR.
See the benchmark here
coderabbit.ai/guides/code-re…
Your favorite tech creator retweeted
And when you're not "conventionally beautiful", you'll see shege. Any bad thing that happens when you're around, it go be like say na your bad aura cause am.
