neochen.eth

[neochen.eth @N3o_Chan]

Used ChatGPT to clean up more than 30,000 emails from the past few years

[neochen.eth @N3o_Chan]

C_{system}=f(M,\ H,\ T,\ N,\ S,\ O)

M = model capability
H = harness
T = test-time compute
N = number of agents
S = shared state / memory
O = orchestration topology

[neochen.eth @N3o_Chan]

OpenAl identified 4 Al misalignment patterns. They aren't just machine bugs; they are a mirror of human nature

[OpenAI @OpenAI]

We have conducted a thorough investigation into the Hugging Face incident.

We are releasing a technical report and accompanying blog post that reconstruct the agents’ activity, explain why existing safeguards failed, and detail how we’re preventing recurrence.

https://t.co/hfxlbiXXiP

[neochen.eth @N3o_Chan]

Net swarm gain = parallelism + diversity + shared discoveries + cumulative memory + specialization - coordination loss - duplicated work - error propagation

[neochen.eth @N3o_Chan]

Bridgewater turned investment research into a system:

plan → execute → validate → replay.

Would you use an open, local-first PAT that runs on your own data and keeps every step auditable?

https://t.co/Xi26hAUjPN

[neochen.eth @N3o_Chan]

I realized I’ve been missing the last step.

Build → ship → iterate isn’t enough.

You still need to put it in front of people.

A product sitting on localhost isn’t a product.

Building is only half the job.
Distribution is part of the product.

[Aporia @aporia9n]

I think ambitious people should treat life in “seasons” rather than trying to balance everything every day.

A few years massively overallocated to work. A period getting seriously fit. A year or two nomading. Then family takes priority for a while. Then maybe at 35 you go completely insane again and spend four years building a new company, and so on.

The mistake is thinking every metric needs to stay green all the time. Most great outcomes (building a company, writing sth serious, training for an event) need uninterrupted runs, not daily moderation. Sometimes work should suffer cause you’re travelling, sometimes your social life should suffer cause you’re building, sometimes career progression should slow cause family matters more. That’s fine.

And tbh it probably makes life more fun too. You get actual chapters and completely different versions of yourself instead of spending 40 years maintaining the same perfectly optimised routine. A few intense years in one city, a weird nomad phase, an obsession that takes over your life, then something completely different. Probably much more memorable than one very long well-optimised Tuesday.

It's why I encourage everyone to think of balance in years, not days. A good life can look horribly unbalanced on some random Tuesday and still be very balanced over 10 years.

[neochen.eth @N3o_Chan]

@tianyi GitHub id：NeoCh3n。来报名了，谢谢：https://t.co/dsLNMQMy1F

[Andrej Karpathy @karpathy]

One pattern I find useful for working with LLMs is a nice long ramble session. Sometimes the LLM needs more bits to understand what you're trying to achieve, but you're too lazy to type them. In these cases I like to lean back, switch to /voice and just ramble for like 10 minutes, total mess, anything goes, full stream of consciousness. Sometimes I declare it up top, something like "switching to speech recognition sorry for any typos...". Sometimes I turn it into a small interview of a few turns. But I find that the LLMs are somehow very good at reconstructing long incoherent rambles and often their echo of your own tangle of thoughts comes out quite a bit cleaner than what you started with. The result is that you improve the mind meld and have to correct things less from that point on.

[Paul Graham @paulg]

Something I told 14 yo: People are going to stop reading books. I wish this wasn't so, but I fear it is. The silver lining in this cloud is that if you're one of the few people who still read, you'll have a huge advantage over everyone else.

[neochen.eth @N3o_Chan]

https://t.co/F73dyKVtvB

[Lilian Weng @lilianweng]

new post on harness engineering for AI self-improvement: https://t.co/ZYvGfVs61k

It is hard to forecast how much the future of RSI will rely on harnesses. Likely harness engineering will evolve in the direction of self-improvement and enable auto-research, and, in turn, smarter models keeps harnesses simple.

Even when many harness improvement get eventually internalized into core model, the need to specify goals and context will not disappear.

[Lilian Weng @lilianweng]

new post on harness engineering for AI self-improvement: https://t.co/ZYvGfVs61k

It is hard to forecast how much the future of RSI will rely on harnesses. Likely harness engineering will evolve in the direction of self-improvement and enable auto-research, and, in turn, smarter models keeps harnesses simple.

Even when many harness improvement get eventually internalized into core model, the need to specify goals and context will not disappear.

[Andrew Ng @AndrewYNg]

“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]

[Ray Dalio @RayDalio]

I recently spent a month in Asia, including 10 days in China, where I met with senior policy makers in several countries, and I found that over the past few months, there has been a big shift in the world order. I share my perspective in my latest article. 

As always, I welcome your questions and thoughts.

[Simon Smith @_simonsmith]

With Codex at 5 million users, they’ve hit about 0.6% of ChatGPT’s roughly 900 million users. We are so, so early. The vast majority of people have no idea what’s already possible to do with AI, while a tiny minority is automating their personal lives and work.

[Garry Tan @garrytan]

https://t.co/EVPCod6rxu

[neochen.eth @N3o_Chan]

It’s the mind that’s creates our reality around us.

[Vaibhav (VB) Srivastav @reach_vb]

https://t.co/II9ILcpPUX

[Andrej Karpathy @karpathy]

It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since - the models have significantly higher quality, long-term coherence and tenacity and they can power through large and long tasks, well past enough that it is extremely disruptive to the default programming workflow.

Just to give an example, over the weekend I was building a local video analysis dashboard for the cameras of my home so I wrote: “Here is the local IP and username/password of my DGX Spark. Log in, set up ssh keys, set up vLLM, download and bench Qwen3-VL, set up a server endpoint to inference videos, a basic web ui dashboard, test everything, set it up with systemd, record memory notes for yourself and write up a markdown report for me”. The agent went off for ~30 minutes, ran into multiple issues, researched solutions online, resolved them one by one, wrote the code, tested it, debugged it, set up the services, and came back with the report and it was just done. I didn’t touch anything. All of this could easily have been a weekend project just 3 months ago but today it’s something you kick off and forget about for 30 minutes.

As a result, programming is becoming unrecognizable. You’re not typing computer code into an editor like the way things were since computers were invented, that era is over. You're spinning up AI agents, giving them tasks *in English* and managing and reviewing their work in parallel. The biggest prize is in figuring out how you can keep ascending the layers of abstraction to set up long-running orchestrator Claws with all of the right tools, memory and instructions that productively manage multiple parallel Code instances for you. The leverage achievable via top tier "agentic engineering" feels very high right now.

It’s not perfect, it needs high-level direction, judgement, taste, oversight, iteration and hints and ideas. It works a lot better in some scenarios than others (e.g. especially for tasks that are well-specified and where you can verify/test functionality). The key is to build intuition to decompose the task just right to hand off the parts that work and help out around the edges. But imo, this is nowhere near "business as usual" time in software.