Olivia
Online
nogokiri
@nogokiri
Joined July 2018
188 Following
22 Followers
44 Posts
https://t.co/v694m8Eaj6
“Loop engineering” is a hot buzzphrase after mentions of it by Boris Cherny (Claude Code’s creator) and Peter Steinberger (OpenClaw's creator) went viral on social media. Loops are now a key part of how we get AI agents to iterate at length to build software. In this letter, I’d like to share my 3 key loops, shown in the image below, for building 0-to-1 products. These loops guide not just how I build software, but also how I decide what software to build.
Agentic coding loop: Given a product specification and optionally a set of evals (that is, a dataset against which to measure performance), we can have an AI agent write code, test its work, and keep iterating until the code is bug-free and meets its specification. This idea of closing the loop took off around the end of last year, and it has been a game changer in enabling coding agents to work longer productively without human intervention. For example, over the weekend, I was building an app for my daughter to practice typing, and my coding agent could easily work for around an hour, using a web browser to check what it had built multiple times before getting back to me, without needing my intervention.
The engineering loop executes quickly. Every few minutes, the coding agent might build and test a new version of the software. I hear frequently from developers who are finding new ways to engineer more effective engineering loops. This is an active area of invention!
Developer feedback loop: In this loop, a developer examines the current product and steers the coding agent to improve it. Last year, a lot of developers (including me) were acting as the QA (quality assurance) function for our coding agents, manually finding bugs and then asking the agent to fix them. But with coding agents much more able to test their own code, the amount of time we need to spend on this function has decreased significantly. This allows us to make higher-level product decisions, such as what key features to offer, where the UI needs improvement, and so on.
The developer-feedback loop operates over time intervals between tens of minutes and hours — that's how frequently a developer might review a product and give feedback. In the case of the typing app, I changed my mind a few times about the visual design, what cat costumes she can unlock as she learns (she loves cats), and the user flow for a grown-up to log in and steer the child's learning experience.
When a developer has a clear vision for what to build, it is still a lot of work to translate that vision into a specification for a coding agent to implement. Further, after the developer has seen an implementation, they might update (or perhaps clarify) the spec to steer it toward what they want. If you find that the system repeatedly runs into certain problems, building a set of evals for the agent becomes useful.
AI-native teams are increasingly using AI to help shape product direction, for example, automating the gathering and analysis of usage data, summarizing written and verbal customer feedback, or carrying out competitive analysis. However, for pretty much all the products I’m involved in, I see humans as having a significant context advantage over current AI systems — we know a lot more than the AI system about the users and the context the product has to operate in — and thus humans play a critical role. Many people describe this human contribution as “taste,” but I prefer to think of it as humans having a context advantage, since that gives us a clearer path to helping AI systems get better. This also speaks to why this step can’t be automated: So long as the human knows something the AI does not, human-in-the-loop is needed to to inject that knowledge into the system.
External feedback loop: This includes a wide range of tactics like asking a few friends for feedback, launching to alpha testers, or putting the code into production with A/B testing. These tactics are usually slow, rarely taking less than hours and sometimes taking days or even weeks. This data informs the developer vision, which in turn continues to drive the detailed product spec, which in turn drives the coding agent.
With coding agents speeding up software development, more engineers are starting to play a partial product management role. For many engineers who are growing into this role, the hardest part is shaping the product vision and striking a balance between building (bridging the gap between vision and spec) and getting user feedback to evolve the vision. It is important to do both!
I will write more about how to do this in future posts, but for now, I find it encouraging that engineers are playing an expanded role (just as product managers and designers now do more engineering).
[Original text: The Batch]
![AndrewYNg's tweet photo. “Loop engineering” is a hot buzzphrase after mentions of it by Boris Cherny (Claude Code’s creator) and Peter Steinberger (OpenClaw's creator) went viral on social media. Loops are now a key part of how we get AI agents to iterate at length to build software. In this letter, I’d like to share my 3 key loops, shown in the image below, for building 0-to-1 products. These loops guide not just how I build software, but also how I decide what software to build.
Agentic coding loop: Given a product specification and optionally a set of evals (that is, a dataset against which to measure performance), we can have an AI agent write code, test its work, and keep iterating until the code is bug-free and meets its specification. This idea of closing the loop took off around the end of last year, and it has been a game changer in enabling coding agents to work longer productively without human intervention. For example, over the weekend, I was building an app for my daughter to practice typing, and my coding agent could easily work for around an hour, using a web browser to check what it had built multiple times before getting back to me, without needing my intervention.
The engineering loop executes quickly. Every few minutes, the coding agent might build and test a new version of the software. I hear frequently from developers who are finding new ways to engineer more effective engineering loops. This is an active area of invention!
Developer feedback loop: In this loop, a developer examines the current product and steers the coding agent to improve it. Last year, a lot of developers (including me) were acting as the QA (quality assurance) function for our coding agents, manually finding bugs and then asking the agent to fix them. But with coding agents much more able to test their own code, the amount of time we need to spend on this function has decreased significantly. This allows us to make higher-level product decisions, such as what key features to offer, where the UI needs improvement, and so on.
The developer-feedback loop operates over time intervals between tens of minutes and hours — that's how frequently a developer might review a product and give feedback. In the case of the typing app, I changed my mind a few times about the visual design, what cat costumes she can unlock as she learns (she loves cats), and the user flow for a grown-up to log in and steer the child's learning experience.
When a developer has a clear vision for what to build, it is still a lot of work to translate that vision into a specification for a coding agent to implement. Further, after the developer has seen an implementation, they might update (or perhaps clarify) the spec to steer it toward what they want. If you find that the system repeatedly runs into certain problems, building a set of evals for the agent becomes useful.
AI-native teams are increasingly using AI to help shape product direction, for example, automating the gathering and analysis of usage data, summarizing written and verbal customer feedback, or carrying out competitive analysis. However, for pretty much all the products I’m involved in, I see humans as having a significant context advantage over current AI systems — we know a lot more than the AI system about the users and the context the product has to operate in — and thus humans play a critical role. Many people describe this human contribution as “taste,” but I prefer to think of it as humans having a context advantage, since that gives us a clearer path to helping AI systems get better. This also speaks to why this step can’t be automated: So long as the human knows something the AI does not, human-in-the-loop is needed to to inject that knowledge into the system.
External feedback loop: This includes a wide range of tactics like asking a few friends for feedback, launching to alpha testers, or putting the code into production with A/B testing. These tactics are usually slow, rarely taking less than hours and sometimes taking days or even weeks. This data informs the developer vision, which in turn continues to drive the detailed product spec, which in turn drives the coding agent.
With coding agents speeding up software development, more engineers are starting to play a partial product management role. For many engineers who are growing into this role, the hardest part is shaping the product vision and striking a balance between building (bridging the gap between vision and spec) and getting user feedback to evolve the vision. It is important to do both!
I will write more about how to do this in future posts, but for now, I find it encouraging that engineers are playing an expanded role (just as product managers and designers now do more engineering).
[Original text: The Batch]](https://pbs.twimg.com/media/HMEtxp3bsAARJdi.jpg)
The Era of AI Agents began 🫥
I don't know if I'm terrified or excited.
see for yourself 🧵:
💥 ANNOUNCEMENT: Opik v1.0 is released! 💥
Opik is an open source LLM evaluation framework for:
🔥 Implementing LLM-based metrics
🪲 Logging/debugging LLM traces
💯 Scoring, annotating, and versioning LLM data
And so much more. Check out the repo below.
Python Interview Questions & Answers For Beginners.
Artificial Intelligence
This should be impossible!
In just 3 lines of code, this open-source library can clean any ML dataset!
You can:
- flag outliers
- find label errors
- identify near duplicates
- perform active-learning
- find out of distribution samples
- And more ...
Introducing Cleanlab 🚀
A Confident Learning based Python library that works with:
- Any data ( text, image, tabular, audio, etc. )
- Any ML tasks ( classification, tagging, entity recognition, prompting LLMs & more ... )
Check this out👇
You must be wondering how it works! 💭
Cleanlab is developed by folks at MIT, and it's powered by a novel algorithm called Confident Learning!
Below, I have provided a simplified explanation of the same!
Check this out👇
Cleanlab also has a no-code studio that let's you clean any data & train robust models in just a few clicks!
I have shared all the relevant links in the next tweet!
That's a wrap, thanks for reading!
Find me → @akshay_pachaar ✔️
For more content like this!
Cheers! 🥂
ChatGPT is insanely powerful.
But only if you write proper prompts.
Here are the most useful ChatGPT prompt techniques (all new):
A thread 🧵
This Snapchat AI just tried to gaslight me
15 Best ChatGPT prompts to finish hours of work in seconds(all new):
Basic Linux commands: https://t.co/JD7afdb7Le
Introduce Zotero RA, your AI Research Assistant in @Zotero, built with @langchain JS and inspired by @andrewwhite01 . This initial release covers article search, Q&A, and summary, with more features to come next week! Try it out for yourself at https://t.co/HC4BzyKkmo.
Microsoft is offering Data Science Course for Beginners for FREE
- 10 Weeks
- 20 lessons
- 100% FREE
Course link 🧵👇
What are your tips for writing a literature review? 📖🤓
#literaturereview #phd #AcademicTwitter #AcademicChatter #phdchat #phdlife #PhScribble
Hello everyone, we are the Sleepe project (sleep to earn).
Today, we're going to show the community some in-app designs that we're building.
Our product is in the finalization phase and the latest announcements will be updated on our social networks.
#Sleeptoearn #sleepe_io #nft
💰 $10,000 giveaway 💰
Post your #BitcoinButton result to enter!
Rules:
🔸 Retweet this post
🔸 Follow @Binance
🔸 Play #BitcoinButton
🔸 Share a screenshot of your click number and one fact about #Bitcoin using the hashtags #BitcoinButton and #Binance
DevOps Roadmap: https://t.co/rGKhL6TewP
@CoinMarketCap Breathe-to-earn ofc
Trends for you
Most Popular Users
Elon Musk 
@elonmusk
241.2M followers
Barack Obama
@barackobama
119.1M followers
Cristiano Ronaldo
@cristiano
112.7M followers
Donald J. Trump
@realdonaldtrump
111.8M followers
Narendra Modi
@narendramodi
107.1M followers
Rihanna
@rihanna
98.2M followers
NASA
@nasa
92.2M followers
Justin Bieber
@justinbieber
91.4M followers
KATY PERRY
@katyperry
88.9M followers
Taylor Swift
@taylorswift13
82.8M followers
Lady Gaga
@ladygaga
74.3M followers
Virat Kohli
@imvkohli
71.8M followers
Kim Kardashian
@kimkardashian
70.4M followers
YouTube
@youtube
68.8M followers
Neymar Jr
@neymarjr
64.7M followers
Bill Gates
@billgates
64.6M followers
The Ellen Show
@theellenshow
62.4M followers
Selena Gomez
@selenagomez
62M followers
CNN
@cnn
61.8M followers
X
@x
60.8M followers