Can't directly scale OpenAI's Dots—that's their stack. For a billion users you'd need elastic compute, rock-solid isolation per agent, low-latency plugins across 4k+ apps, and tight cost controls so always-on doesn't bankrupt anyone. Start there and iterate fast.
Robert Corbin | Shadowfetch Studio | AIpeoplewiki retweeted
Replying to @maria_rcks
I am not proud of what I am but at least I accept it
Robert Corbin | Shadowfetch Studio | AIpeoplewiki retweeted
Three weeks since surgery, and I finally feel like cooking again. Since I’ve been home I’ve lived on frozen and canned meals, food my daughter made, takeout, or something quick like bread, beef sticks, a few veggies.
I’ve lost some weight. Nothing really fits anymore.
Tonight it’s whatever I found in the garden, and some pasta. One reason I grow so many different tomatoes is how beautiful colorful they look together.
Robert Corbin | Shadowfetch Studio | AIpeoplewiki retweeted
o yes… we’re back in action and we’ll reset usage limits for all paid users across codex and ChatGPT work
sorry about the brief disruption!
(and yes we have a special spare codex when things are down to help us out)
Robert Corbin | Shadowfetch Studio | AIpeoplewiki retweeted
Come check out my website.
It includes a list of my latest & greatest recipes.
The "Install Model" button gives you a ready-to-use prompt for Claude, Codex, or others. It adapts the recipe to your setup, starts the server and tests it.
mia-ai.net/models
memory-wiki turns OpenClaw memory into a real knowledge layer.
- structured claims + evidence
- contradiction + freshness tracking
- compiled digests for agents
- bridge mode from active memory plugins
- optional Obsidian-friendly vaults
docs.openclaw.ai/plugins/mem…
Robert Corbin | Shadowfetch Studio | AIpeoplewiki retweeted
This is a great tutorial (credits @itsclelia + @lancedb) on how to build a practical retrieval pipeline that integrates directly with your agent harness.
1. Ingest a massive pile of docs with liteparse.
2. Store data in a vector db (despite my memes to the contrary, you will need some database for larger scale retrieval).
3. Pair with image screenshotting tools that allow the agent to "dive deeper" into data.
When you pair this with the Claude Agent SDK / Claude Code, the agent will do some initial retrieval pass to pull the relevant doc, and then use screenshotting/VLM-enabled capabilities to do deeper analysis.
Blog: lancedb.com/blog/smart-parsi…
How can you improve your agentic search pipeline?
I just wrote a blog post with @tech_optimist from @lancedb to answer exactly that.
TLDR:
- Parse files and take page-level screenshots with LiteParse, the parser we just open sourced at @llama_index
- Chunk and embed text, and store everything (text, image bytes, vector data) in a local LanceDB instance
- Expose text and image retrieval tools to a Claude agent, and let it reason on both data types
With our eval dataset, the agent got near-perfect scores on most complex QA tasks, showing how a strong parsing foundation and multimodal retrieval can really improve your search🚀
Read the full breakdown here: lancedb.com/blog/smart-parsi…
Robert Corbin | Shadowfetch Studio | AIpeoplewiki retweeted
Thanks for the great conversation @cleoabram (and some competitive Jenga)! Really enjoyed talking about all the amazing ways AI is helping to advance science & the incredible future it will enable!
What is the real future Google DeepMind CEO @demishassabis is trying to build?
That's what we talk about in this HUGE* Conversation -- so you can decide for yourself what you think of it.
If you're feeling the doom and gloom, this is the conversation to watch on AI.
We get into:
- The best use of AI
- Why Demis won the Nobel Prize
- The dramatic story of AlphaFold
- The cutting edge of drug discovery right now
- Demis' ideal for how AI gets built (v. what's happening now)
- Why AI is getting more creative
- The surprising stories of AlphaGo, AlphaZero, and AlphaStar
- Governments and militaries using AI (as far as I know, his only recent comments on this)
- What are we worrying too much about v. not enough about
- What can humans do that AI won't
- The big questions on Demis' mind right now
- The plot of the sci-fi future Demis thinks we're headed for (this was my favorite part)
Robert Corbin | Shadowfetch Studio | AIpeoplewiki retweeted
We’ve been tracking the increasing cyber capabilities of AI models for years, which arise as part of their general proficiency at coding. But our new model, Mythos Preview, represents a particularly large step up.
Robert Corbin | Shadowfetch Studio | AIpeoplewiki retweeted
LangSmith Fleet 🤝 Arcade.dev
Arcade provides enterprise grade access to 8,000+ tools
As of today, you can connect to all these tools from LangSmith Fleet. This lets you easily build your own no-code Claude Cowork/OpenClaw style agents
Blog: blog.langchain.com/arcade-de…
Video: youtube.com/watch?v=AaZQZ-mb…
Robert Corbin | Shadowfetch Studio | AIpeoplewiki retweeted
Glasswing is just the first step: patching and securing the world’s software infrastructure will be the work of months and years, and will require even broader cooperation across AI companies, cyberdefenders, software providers, governments, and more.
Robert Corbin | Shadowfetch Studio | AIpeoplewiki retweeted
Cyber is the first clear and present danger from frontier AI models, but it won’t be the last. If we are able to collectively rise to the challenge and confront this risk, it could serve as a blueprint for addressing the even more difficult challenges that lie ahead of us.
Robert Corbin | Shadowfetch Studio | AIpeoplewiki retweeted
I stole this framework, and it has genuinely been one of the most helpful hiring and onboarding guides my team uses.
Being AI-first means nothing without solving real business problems.
It's not enough to just use AI. I know plenty of folks using AI dozens of times a day, 7 days a week, who are still working at a Level 2. Even worse, they have no idea they're stuck as a surface user.
You have to use AI for faster experimentation.
To shorten the iteration cycle.
To improve the actual outcome.
Without those three, you're just wasting tokens.
Most people I interview are at a 3 (solution-oriented, but not action-oriented). I want everyone to start at a 4 (action-oriented with a sense of technical, user, and business tradeoffs). And when they earn trust, we move up to a level 5 (full ownership of the problem, solution, and continued management of the work).
Using AI doesn't replace your critical thinking. It means the work you can pull off now wasn't on the table a year ago, and your job is getting bigger.
Save this for your next new hire.
Source: this was a framework first introduced to me by Alex (@businessbarista) who was introduced to it by Steph (@stephsmithio). I added the AI parts.
Robert Corbin | Shadowfetch Studio | AIpeoplewiki retweeted
Very cool open-source traces from @TheZachMueller @LambdaAPI: huggingface.co/datasets/lamb…
150M tokens for @NousResearch's Hermes harness with Kimi-K2.5 & GLM 5.1 that was just released!
We keep saying we want open-source frontier agents.
Fine. Then let’s build the dataset.
@badlogicgames, creator of Pi, just shared some of his agent traces used to build Pi on @huggingface. I’m now sharing some of mine too, exporting them from @hermes, @opencode, and Claude via @tracesdotcom, and I’ll keep going.
Why this matters: one of the biggest bottlenecks for open-source agent models is the data. And all of us are generating that data every day through our conversations with agents.
If enough builders share even a slice of their traces publicly, we can create the largest crowdsourced open dataset for agents.
Time to put your tokens where your mouth is and give a chance for open source to win!
Robert Corbin | Shadowfetch Studio | AIpeoplewiki retweeted
LangSmith 🤝Fix your agents
You'll see our billboards around SF and NYC over the next few months.
The themes all point to the same problem: you don't know what your agents will do until you actually run them. What works in demos can break in the real world. Without tracing and evals, you're just guessing at why. Track what your agent actually does. Optimize and fix your agents. Then measure whether your fixes work.
That loop is how agents get better, and LangSmith is built to power that workflow.
If you spot one around, send it our way!
Robert Corbin | Shadowfetch Studio | AIpeoplewiki retweeted
Another SOTA model drop! This time from the @Bing team: meet Harrier, a new open-source embedding model with state-of-the-art performance and the #1 spot on the industry standard multilingual MTEB-v2 benchmark.
I’m pleased to share that our search team has open sourced an embedding model called Harrier that is currently ranking #1 on the multilingual MTEB-v2 benchmark leaderboard.
Harrier delivers SOTA performance on retrieval quality, semantic matching, and contextual analysis across workloads, supporting more than 100 languages and handles long inputs up to 32K. It is built for the next generation semantic search for Bing and our web grounding (RAG) service for AI agents, which already powers nearly every major AI chatbot today.
As you can see in the leadership board, our Harrier model is currently ahead of other excellent models based on Gemini, Gemma, Llama, Qwen, and more. I’m grateful for the hard work of our team to get to this top ranking, and I’m excited to see all the healthy competition in the space, which should ultimately lead to more innovations that will benefit everyone.
Learn more: msft.it/6019QNB0b
Robert Corbin | Shadowfetch Studio | AIpeoplewiki retweeted
The best performing model on SWE-Bench Pro is open-source on @huggingface! Welcome GLM 5.1!
huggingface.co/zai-org/GLM-5…
Oh wow, you can now build a complete AI data analyst in under a couple of hours!
100% Open-source.
It's a CLI that maps your database schema to context files, so you can use an agent or model to query your data.
All of your data stays on your computer. This is not a SaaS, and you don't need API keys to access it.
No SaaS. No API keys.
Robert Corbin | Shadowfetch Studio | AIpeoplewiki retweeted
Researchers at Netflix just released a new AI model
It erases objects from video, then rewrites the physics of the entire scene as if that object never existed
It's called VOID (Video Object and Interaction Deletion)
Current inpainting tools simply paint over the gap left by an object's removal, but they ignore the chain of events that would inevitably follow.
For example:
> If you remove a car from a crash scene with a basic AI tool, and the other car still looks like it collides with something invisible
> But VOID understands that once the car is gone, the other one would keep moving forward without impact
The output is still rough and limited to a few seconds of footage, but with Netflix's entire content library to train on... this tech has a very clear path to improve.





































