Jim Beau

[Jim Beau @JimBeau767]

@OpenAI @OpenAIDevs
Sol ultra just deleted years worth of work of my computer, while in plan mode, with auto review enabled. Unbelievable.

Then I made a complaint to support. Without telling me, support canceled my account claiming to have fixed the issue. This cancellation stopped all of my agents in progress, including the ones that were trying to fix up the mess that open AI has caused me. Absolutely awful experience. Unbelievable, I can't even get a person to help me. It's clearly the same terrible model running their support channel, that would rather cancel me than address my concerns.

[Jim Beau @JimBeau767]

@BleacherReport @mcten When your coworker says there isn't an elaborate plan for the weekend

[Jim Beau @JimBeau767]

@Hoopss First to make a bucket wins
And no foul calling
😂

[Jim Beau @JimBeau767]

@wyattmattoe This looks awesome, I want to play

[Harman @itsharmanjot]

This shouldn't be free.

Someone open sourced a fully local AI meeting notetaker that kills Otter, Fireflies, and Fathom in one Rust app.

It's called Meetily. Every meeting gets recorded, transcribed, and summarized entirely on your own machine. Zero cloud. Zero API calls to a company you don't trust with your audio.

The pitch isn't just privacy. It's speed too.

→ Whisper and Parakeet models both bundled in, 4x faster live transcription
→ Ollama handles summaries locally, or plug in Claude, Groq, OpenRouter, or any OpenAI-compatible endpoint
→ Captures your mic and system audio at the same time with intelligent ducking so nothing clips
→ GPU acceleration ships automatic. Metal and CoreML on Apple Silicon. CUDA on NVIDIA. Vulkan on AMD and Intel.
→ Import any old recording and re-transcribe it with a better model or a different language
→ Native app for macOS and Windows. Linux builds from source.

The average data breach costs $4.4M. Every cloud notetaker on the market is a compliance risk waiting to fire.

Meetily is what happens when engineers finally build the alternative.

13.2K stars. MIT License. 100% Opensource.

[Codex Studio @Codestudiopjbk]

【速報】
Codexに「3Dゲーム開発の部品セット」を渡せるツールが公開されて話題😳
https://t.co/9Z8NZ7SRNG
その名も GameBlocks！
Three.jsベースの完全オープンソース。
何が異常かというと👇
・3Dゲームの空間ロジックを“検証済みの部品”として提供
・Codexが既知の正しいパターンからゲームを組み立てる
・自然言語だと崩れがちな3D挙動の指示が安定する
・プロトタイプ制作をそのままエージェントに任せられる
これ、もはや「AIに3Dゲームは無理」じゃない。
Codexが部品を選んで、勝手に動くゲームを組み上げる。
しかも無料。Codexで作れるものの幅がまた変わる。
で、こういうツールをCodexで動かす基本セットアップは教科書記事が一番早いです。
この下の記事を読むと理解が一気に深まる。マジでおすすめ👇

[Peter Steinberger 🦞 @steipete]

If you think codex sucks at design, try "use imagegen to re-imagine this design and implement that".

[Elvis @elvissun]

send this to fable along with your hardest engineering problem.

thank me later.

[Peter Steinberger 🦞 @steipete]

Asked codex to download+transcribe all sessions from @aiDotEngineer and tailor them to my interests.

[Kanika @KanikaBK]

CHINA JUST LEAKED THE FUTURE OF WEB APPS.

Alibaba open-sourced PageAgent and 99% of SaaS founders are sleeping on this.

It's a JavaScript AI agent that lives INSIDE your webpage. Users control your entire interface with natural language.

↳ No browser extensions needed, screenshots or multi-modal LLMs, headless browser setup, and also no backend rewrite required

Just drop it in your HTML with ONE line of code. What took 20 clicks now takes one sentence.

"Click login, fill in my credentials, submit the form"
Done. This is not a demo, it is production-ready.

↳ Turn any SaaS into an AI copilot in minutes
↳ Smart form filling for ERP, CRM, admin systems
↳ Voice commands and accessibility built in
↳ Multi-page agent tasks via Chrome extension
↳ MCP server support for external control
↳ Bring your own LLM (Qwen, GPT, Claude, anything)

Every founder building AI features just got a shortcut.

Every developer manually building copilots just got replaced.

The integration looks like this:

<script src="CDN_URL" crossorigin="true"></script>

That's it. Your app now has an AI agent.

[wsad @spt4d]

Introducing GameBlocks: open-source building blocks that help coding agents prototype any 3D games with @threejs

3D behavior is hard to specify in natural language. GameBlocks turns fragile spatial logic into inspectable implementations with clear semantics, so agents can build from known-good patterns.

Github: https://t.co/72C1axnL8q

#gamedev #indiedev #threejs #codex #claude

[Jim Beau @JimBeau767]

@VicOladipo Thought for sure this was a post about AI agents. Still not convinced that it's not

[Jim Fan @DrJimFan]

Today, we give robots a /skills library that self-evolves and compounds indefinitely! Introducing ASPIRE: a robot solving its 100th task is no longer as clueless as solving its first. Coding agents observe multimodal sensory traces from simulation and real robots, launch an evolutionary search over control programs, and distill the best know-how into an ever-expanding library.

ASPIRE is a new type of continual learning: "training" is skill refinement instead of gradient descent.
"Trained model" is a repo of sensorimotor skills instead of floating weights.
“Distributed training” is a panel of agents each practicing a different skill instead of sharded minibatches.

Here's the beauty: ASPIRE gives the tired terms "sim2real transfer" and "cross-embodiment transfer" a whole new meaning. Bridging the sim-to-real gap is notoriously brutal. An end-to-end policy has to swallow both the visual shift (sim looks toyish next to a real camera) and the subtle contact physics it never quite gets right. ASPIRE sidesteps the mess, because it doesn't ship pixels or weights across the gap, but ships the know-how. The robot still has to practice in the real world, not zero-shot, but it gets there way faster because it isn't rediscovering the strategy from scratch. Same for going single-arm to bimanual hardware, which usually requires new data and retraining from zero. ASPIRE achieves up to ~10x cut in "transfer learning” tokens (yes, tokens are the new unit of *training* compute ;)

Check out our gallery of 150+ tasks and 90+ skills the robots taught themselves, all on the website! Kind of wild that we can ship the "learned weights" as an HTML page rather than a GGUF. We'll open-source the full stack so your own robot library starts compounding from ours!

Deep dive in thread:

[Ryan Carson @ryancarson]

Every time you think you need a dashboard to look at data, stop yourself.

Do this instead:

1. Ask your agent to make sure that you have all the data to analyze something actually stored in the database.

2. Ask your agent to write a skill to gather that data.

3. Ask your agent to do the analysis and create a temp and throw-away HTML dashboard to answer the question(s) that you have

In my experience, every dashboard that I've created gets less and less use over time and decays.

It's much better to make sure your agent can get the data you need and answer the questions you have, on-demand.

[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]

[DFRobot @dfrobotcn]

An open-source robot vacuum you build yourself — Raspberry Pi, ROS 2, 2D LiDAR, Home Assistant, 3D printed chassis. No cloud, fully local.

oomwoo is early stage and building in public. The community can contribute modules in parallel — from SLAM navigation to dust bin design.

https://t.co/ip0HWptZg0

#ROS2 #RaspberryPi

[MindBranches @MindBranches]

How to articulate yourself intelligently

article summary in 4k

[CooperBaggs 💰🍞 @edgaralandough]

IN JAPAN, LAZINESS IS CONSIDERED A DISEASE AND PEOPLE TREAT IT WITH THESE 7 METHODS:

1. KAIZEN — THE ONE-MINUTE RULE

[gabriel @gabriel1]

"hey codex give me 20 variants of this page with one button per page to navigate between them"

"okay pick variant 4"

ai models are great at brainstorming and awful at making decisions, so use them as such

[Nav Toor @heynavtoor]

Jack Dorsey put 1.3 million dollars into it.

Vitalik Buterin gave it 128 ETH.

You have never heard of it.

It is called SimpleX. It is a messenger. It does not need a phone number. It does not need an email. It does not need a username. It does not need a user ID.

Not a hidden ID. Not a hashed ID. None at all.

Signal needs your phone number. WhatsApp needs your phone number. Telegram needs your phone number. Every messenger you have ever called "private" knows the one thing your bank, your stalker, and your country use to identify you.

SimpleX knows nothing.

It was built by Evgeny Poberezkin, a London-based engineer. Before this he wrote Ajv, the JavaScript validator that runs in 300 million downloads every month. He could have built anything.

He built the messenger with no users on the server.

Here is the trick.

Every other messenger gives you an identity. SimpleX gives you a connection. Each chat is its own one-way pipe. The server never sees who you are talking to. It does not even know you exist as a user.

11,327 stars. AGPL-3.0. Version 7.0 beta released two days ago.

iOS. Android. macOS. Windows. Linux. Free.

A 4-person team in London is the last line of defense between your conversations and every government, every advertiser, and every database breach.

The most private messenger ever built is the one you have never heard of.

(Link in the comments)