You’ve misunderstood how AI works. why not ask the chatbot which sources it relied on to arrive at that conclusion? Instead of taking its answer at face value without verifying the sources
After all the tears. Don’t forget that Peter Obi still remains number one regardless of tribe.
So yes. Ain’t no crime voting my ‘tribe’ especially becomes he ranks number one.
That ain’t bigotry. It is simply the right thing to do.
2
224
Adedotun | AI Engineer 🧠 retweeted
DeepMind CEO Demis Hassabis:
"One person who really understands AI will outperform an entire startup team
In 5 years, the people who build with AI will run whole companies with a tenth of the headcount"
“Build and Deploy your own LLM application”
80 Machine Learning Project Ideas.
Grab Machine Learning Project Handbook: codewithdhanian.gumroad.com/…
43
Now this is a tool we all need.
1/ Today we're introducing Breken, and with it the final job in software: production engineering.
Your tests check what your team thought of. Production checks everything else. Today, your users run that second test for you.
Breken runs it instead. Your real software, in worlds that behave like production, down to the chaos and the users, finding and fixing what breaks before a single user does.
Here it is: breken.ai
39
there's a big opportunity in AI advisory right now, a gap in the market that's waiting to be filled...
atm there are two types of "AI experts":
the AI normie
- know how to use tools but completely delegate his thinking
- don't think in systems
- can't implement AI in real business workflows
the full AI nerd
- know everything there's to know about AI
- has 10 Claude Code instances running his life
- can't communicate with an human
and this is where YOUR opportunity is...
the market is screaming for a third type: the AI advisor
someone who can walk into a business, look at their operations for 2 hours, and say "this process right here? AI cuts it by 40% and here's exactly how"
they're looking for that guy who's deep enough in the rabbit hole to fix their problems, but also smart enough to dumb things down so they can understand the solution
be that guy
Adedotun | AI Engineer 🧠 retweeted
Replying to @dontforgetchaos
Websites are files on a computer. When you view a website, you are asking the computer to send you the files, then your browser shows them to you.
70% of the websites you see use PHP to make them interactive. So you can send things to the website too and it can respond. E.g. filling in a comment box and hitting 'post' adds the comment as a row to a spreadsheet.
PHP has a flaw in its code that allows anyone to gain control of the computer that has the website on it.
The organisation that provides PHP announced the vulnerability before a patch was available, meaning we're in a window where everyone knows about it (including baddies) but the good guys don't have an official solution.
Some are just turning off their websites and waiting for the solution. Others are trying to fix it themselves. General chaos and lots of stressed techies across literally the entire planet because this affects the entire internet.
A RAG technique is not automatically better because it sounds more complex.
Your document structure, retrieval needs, latency, cost and failure cases should guide your choice.
Start simple, evaluate with realistic questions and let the evidence decide.
#RAG #AIEngineering #GenAI
1
23
Adedotun | AI Engineer 🧠 retweeted
GOOGLE HAS RELEASED SOMETHING NO ONE EXPECTED.
An 8-minute tutorial on how to build your first AI agents.
While learning AI engineering with ChatGPT, I asked it to save my learning path to memory so it could refer back to it in future conversations
That way, even when the context window gets full,I can pick up where I left off
understanding AI limitations let’s you get more out of it
Precision, recall, true positives, true negatives, false positives, and false negatives aren’t just machine learning concepts. They’re essential tools for AI engineers evaluating model performance and reliability
You can’t improve what you don’t properly evaluate
#AIEngineering
18
Today I tested size-based chunking for a RAG support assistant: 400-token chunks, 100-token overlap, then removed duplicated overlap before generation.
Top-2 retrieval scored 75%. Top-3 scored 87.5% but used 37% more tokens.
Next: section-aware chunking.
#RAG
12
This is crazy
REA (Reverse Engineer Anything) by @morluto is now a skill in Computer.
Ask Computer to reverse-engineer an app and it inspects how the app works without its source code, then builds a working version.
Tasks that use /reverse-engineer are free through October 31, up to 10,000 credits per user.
Here are 5 apps Computer made with it, available to try for a limited time:
1) Figma: Design with layers and auto-layout, plus sign-in, cross-device sync, and multiplayer editing. Try it: ui-editing.pplx.app
16
New voices. Better accents. And less "checking..."
GPT-Live-1.1 brings these updates to Voice in ChatGPT, Codex, and dots, with new voices in French, German, Hindi, Mexican Spanish, Korean, and Japanese.
Rolling out today to all users. Coming soon to the API.
Say hello to GPT-Live-1.1
Learning the OpenAI Realtime API today, and WebSockets are finally starting to make sense. I kept one connection open, streamed a reply, then asked a follow up in the same session and it remembered the context. Next step is adding audio.
#OpenAI #AIEngineering
2
55
Adedotun | AI Engineer 🧠 retweeted
Your AI keeps forgetting important details halfway through a project
The longer your conversation gets, the worse it can become
Here’s a prompt that helps fix it:
“Create a compact project memory from our conversation. Include goals, key decisions, constraints, preferences, completed work, and next steps. Remove unnecessary details but preserve critical context. Format it so I can paste it into a new chat and continue without starting over.”
Stop losing hours explaining the same project to AI over and over again
Earned OpenAI Academy’s Build with RAG badge 🎉
Reliable RAG starts before retrieval: clean messy data, structure documents and choose chunks carefully. Then test with Promptfoo. When a case fails, inspect the model, source and grading rule, and change one thing at a time. #RAG
1
1
52
Adedotun | AI Engineer 🧠 retweeted
If you do not force yourself to improve , nothing in your life will ever will. You already know what needs to be done . Lock in
























