Felicity Onwano

Data Analyst

[Daniel Emeni @Daxcode001]

Nobody talks about how mentally strong you have to be just to be a young Nigerian. We carry a lot quietly. 💙

[Felicity Onwano @f_onwano]

@Templeton193352 @MARINA_PROTOCOL @Girin_Labs @Dhaavid @HELYNofweb3 @karisdann 💵🤑

[Felicity Onwano @f_onwano]

#Microsoft #CSS #webdev
#html5
I decided to share one of the little steps that got me where I am today in web design and development. I do hope it benefits you too. Do well to share to your friends in the field and follow me for more technical contents
https://t.co/McwprnjL0B

[BorderlessDev👨🏼‍💻| @BorderlessDev]

How can I access funding for my project as a #dev 🤔

Join @_karlagod, @greatAdams01, @victorpianwi and @Em_Etok tomorrow as we discuss the myriad of funding opportunities open to Developers and Founders in #web3

🗓️29th March
🕖7pm WAT
📍https://t.co/tUlYDwFM63

#Lisk #web3

[Felicity Onwano @f_onwano]

I'm finally done with this assignment 😁😌🥳🥳

[Andrew Ng @AndrewYNg]

I think AI agentic workflows will drive massive AI progress this year — perhaps even more than the next generation of foundation models. This is an important trend, and I urge everyone who works in AI to pay attention to it.

Today, we mostly use LLMs in zero-shot mode, prompting a model to generate final output token by token without revising its work. This is akin to asking someone to compose an essay from start to finish, typing straight through with no backspacing allowed, and expecting a high-quality result. Despite the difficulty, LLMs do amazingly well at this task!

With an agentic workflow, however, we can ask the LLM to iterate over a document many times. For example, it might take a sequence of steps such as:
- Plan an outline.
- Decide what, if any, web searches are needed to gather more information.
- Write a first draft.
- Read over the first draft to spot unjustified arguments or extraneous information.
- Revise the draft taking into account any weaknesses spotted.
- And so on.

This iterative process is critical for most human writers to write good text. With AI, such an iterative workflow yields much better results than writing in a single pass.

Devin’s splashy demo recently received a lot of social media buzz. My team has been closely following the evolution of AI that writes code. We analyzed results from a number of research teams, focusing on an algorithm’s ability to do well on the widely used HumanEval coding benchmark. You can see our findings in the diagram below.

GPT-3.5 (zero shot) was 48.1% correct. GPT-4 (zero shot) does better at 67.0%. However, the improvement from GPT-3.5 to GPT-4 is dwarfed by incorporating an iterative agent workflow. Indeed, wrapped in an agent loop, GPT-3.5 achieves up to 95.1%.

Open source agent tools and the academic literature on agents are proliferating, making this an exciting time but also a confusing one. To help put this work into perspective, I’d like to share a framework for categorizing design patterns for building agents. My team AI Fund is successfully using these patterns in many applications, and I hope you find them useful.

- Reflection: The LLM examines its own work to come up with ways to improve it.
- Tool use: The LLM is given tools such as web search, code execution, or any other function to help it gather information, take action, or process data.
- Planning: The LLM comes up with, and executes, a multistep plan to achieve a goal (for example, writing an outline for an essay, then doing online research, then writing a draft, and so on).
- Multi-agent collaboration: More than one AI agent work together, splitting up tasks and discussing and debating ideas, to come up with better solutions than a single agent would.

I’ll elaborate on these design patterns and offer suggested readings for each next week.

[Original text: https://t.co/y4McIAjD2m]

[Bob E. Hayes @bobehayes]

The exponential enshittification of science

"Every article w/ #ChatGPT remnants should be considered suspect and perhaps retracted, because hallucinations may have filtered in, and both authors and reviewers) were asleep at the switch." @garymarcus

https://t.co/x8L1PxgyAE

#AI

[Fei-Fei Li @drfeifei]

One year ago, we first introduced BEHAVIOR-1K, which we hope will be an important step towards human-centered robotics. After our year-long beta, we’re thrilled to announce its full release, which our team just presented at NVIDIA #GTC2024. 1/n

[Fei-Fei Li @drfeifei]

After 3+ years, today is the day that my book “The Worlds I See” gets to see the world itself. It is a science memoir of the intertwining histories of me becoming an #AI scientist, and the making of the modern AI itself. All versions are now on Amazon https://t.co/1oH2vCjovu 1/

[BorderlessDev👨🏼‍💻| @BorderlessDev]

We made progress 🥳🥳

We had 5 more contributors donate to B<>rder/ess in the last 24 hours, let's take it up🥳

Donate now on @gitcoin👇

We're in the @greenpillnet<> @octant round on @Optimism
https://t.co/tXo1iLWtrV

@UnlockProtocol round on @arbitrum
https://t.co/CFERPclNHX

[Felicity Onwano @f_onwano]

Don't miss out on this grrrrrrrreat opportunity
#tech #Scholarship

[BorderlessDev👨🏼‍💻| @BorderlessDev]

📝REGISTRATIONS ARE OPEN🚪🤓 👐🏽

Announcing the April 2024 Cipher Session 🎓🤓

B<>rder/ess is giving 500 #web3 and #tech scholarships to students who want to learn, programming skills, #Blockchain development, #Smartcontract writing, on-chain data analysis, #uiuxdesign and more.

[Felicity Onwano @f_onwano]

@BorderlessDev 🤗☺️

[Felicity Onwano @f_onwano]

To God be the glory ☺️💃🏾

Microsoft Certified: Azure AI Fundamentals https://t.co/0C4bnzso1B

[B-Media 📹 @web3bmedia]

🤝 Community Partnerships 🤝

We're announcing a Community Partnership with the "Association of Catholic Engineering Students" Uniport Chapter (ACES)
https://t.co/CQg3xh5WW5

Together, we're empowering the ACES community with essential #web3 skills, and helping them to prepare for the future of #tech in Nigeria.
🔸
🔸

Register 📲
https://t.co/XP4qaAERBl

🗓️ November 4th
📍Aztech Arcum Event Centre, Stadium Road, Port-Harcourt, Rivers State.
🕙10AM Prompt

#borderless20
#becomingsolutions
#cryptosmart

[Felicity Onwano @f_onwano]

@mlsauniport Thanks 🤗

[Felicity Onwano @f_onwano]

@mlsauniport
https://t.co/xzULgG8jsT
Assignment 1 done✔️☺️☺️

[MLSA, Uniport #frontendDevelopment Bootcamp @mlsauniport]

The Journey to becoming a Front-end Developer starts here.

Join us as we build from scratch

Sign up using this link
https://t.co/qpBVGV5lYM

#studentcommunity
#frontendDevelopment
#MSFTStudentAmbassadors

[David Hundeyin @DavidHundeyin]

Lol @officialABAT why are you deceiving yourself with this dying minute stunt?

Alumni network you didn't join since the dawn of the internet, it's now in August 2023 that you're joining after realising that we're about to expose that fact that you never attended @ChicagoState?

[🏘️IamEri'Oluwa🇳🇬 @IamEriOluwa]

Relationship will always experience the post honeymoon phase.

The chemistry may not survive outside of the honeymoon phase laboratory.

However, common decency is a personal thing. It's important that we date and marry people who at least have common decency to walk out of our lives without destroying it on their way out.

Unfortunately, we live at a time where toxicity sells and it's celebrated. So, check their approach to toxic trends and how they treat personal issues in public.

That right there is your GPS!

[MLSA, Uniport #frontendDevelopment Bootcamp @mlsauniport]

SUMMER BOOTCAMP FOR TEENS&KIDS

Date: 24th July to 24th August 2023
https://t.co/6nqJFK3WPt

#techforkids