←
Timmy Ghiurau5,453 posts
Timmy Ghiurau avatar

Timmy Ghiurau

@itzik009

AI × XR × Culture | Co-founder @MidBrainAi and @thepointlabs | ex-@volvocars innovation lead |Teaching machines to make sense. Nerd by day rock star by night 🎸

◷ Joined September 2011▧ 759 Photos and videos
Timmy Ghiurau avatar
Timmy Ghiurau@itzik009·Nov 17

i want my agent to learn from my corrections, not need the same instructions next week. at midbrain, we're researching how feedback becomes lasting model skills. midbrain.ai/blog/continual-l… i'm at @SlushHQ . building agents or working on continual learning? dm me, let's meet.

Post attachment
Baytaş avatar
⟳ Timmy Ghiurau retweeted
Baytaş@doctorbaytas·Nov 17

you must study HCI research

one of the most brilliant takes i've seen as of late on HCI in the era of LLMs Attention steering by Sun Chuanqi. Actually operating an LLM's attention and token generation. the concept, UX and sound design are just amazing. There are still so many unexplored patterns. this one's particularly inspiring github.com/chuanqisun/spaces…

Timmy Ghiurau avatar
Timmy Ghiurau@itzik009·Nov 12

Taste is never stated. It shows up in the edits. I've never told an agent how I like my emails. I delete "I hope this message finds you well", cut a paragraph and add a next step. Every time. An agent that learns picks it up without being told. What edit do you keep making?

Timmy Ghiurau avatar
⟳ Timmy Ghiurau retweeted
Timmy Ghiurau@itzik009·Oct 19

Building AI that learns while it works. We’ve just launched the new MidBrain website. It brings together our research and product, and gives a clearer picture of where we want to take things. For the past year, we’ve been working on a question: How can each new experience make an AI system more capable? When an agent repeats a mistake you’ve already corrected, you end up doing the same work again. We want that correction to change how it handles the next relevant task. The bigger ambition is that the longer a person or team works with an AI system, the more useful it becomes. It should develop capabilities through experience and retain what it has learned as the work changes. At @MidbrainAI , we’re connecting research in continual learning with infrastructure people can use today. Our product turns feedback into learned procedures agents can apply to future tasks. Our research explores how learning can happen during an interaction itself, and how systems can keep adapting without losing useful knowledge. The new site shares our published research, the questions we’re investigating, and the product you can try. If you’re building agents that need to improve over time, we’d love for you to put MidBrain to work. Try it on a real workflow. Challenge our assumptions and tell us where it falls short. There’s a lot we still need to figure out, and working with people using these systems is part of how we’ll get there. Explore the research and try the product: midbrain.ai

0:48
Timmy Ghiurau avatar
Timmy Ghiurau@itzik009·Nov 12

our minecraft agents forgetting overnight were part of what led us here. this piece traces that story alongside other approaches to AI "dreaming". my test for the idea: does the offline work make the next task better, or just produce a tidier memory?

God of Prompt @godofprompt Nov 11 Article Every AI That Dreams, and Who Got There First Claude dreams now. On 6 November, Anthropic's engineering team showed how it works. Between tasks, Claude rereads the transcripts of its own sessions, checks its saved notes against what actually

MidbrainAI avatar
⟳ Timmy Ghiurau retweeted
MidbrainAI@MidbrainAI·Nov 11

Different coordinates, same similarity. MidBrain stores embeddings after an orthogonal transform derived from each agent's search key. Dot products survive it, so ranking doesn't change.

Post attachment
Timmy Ghiurau avatar
Timmy Ghiurau@itzik009·Nov 11

If an AI agent is going to work with you for years, you should know who can read the history it builds. At @MidbrainAI , we use separate keys for your conversations and documents, the search index, and the preferences and instructions the agent picks up over time. In client-managed mode, you keep the key that decrypts your stored conversations and documents, while the agent can still search them. We wrote up how this works, including what our servers can see when they process a new memory. If you’re building agents that learn from experience, I’d love to hear how you’re handling that trade-off.

Every MidBrain agent gets four keys. The one that decrypts conversations and documents never reaches our servers in client-managed mode. Search and consolidation get only the key they need.

Post attachment
MidbrainAI avatar
⟳ Timmy Ghiurau retweeted
MidbrainAI@MidbrainAI·Nov 9

Most failures in our DolphinBench run came after the facts reached the model. 89.1%: right tool, facts in context, response omitted a requirement. 7.9%: retrieval misses. 3.0%: expected tool never called.

Post attachment
proxima centauri b avatar
⟳ Timmy Ghiurau retweeted
proxima centauri b@proximasan·Nov 10

had to make the national anthem of europe with this

3:11

my vocal synth models the vocal tract as a network of branching acoustic tubes, unlike vocaloid which stitches together and pitch-shifts phoneme recordings. still working on improving naturalness by tuning it against recordings of real singers, but I'm already impressed at how cool it sounds!

2:25
Boris Cherny avatar
⟳ Timmy Ghiurau retweeted
Boris Cherny@bcherny·Nov 9

We wanted to do more for the people who’ve been with us the longest. So with Fable 5.2, the longer you’ve been subscribed, the more Fable resets you get.

Post attachment

Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges. They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.

0:19
Timmy Ghiurau avatar
Timmy Ghiurau@itzik009·Nov 9

An agent can have the right facts in front of it and still miss a requirement. That’s what stood out to me in our DolphinBench failure analysis. It raises the next question for us: how do we make remembered context translate into reliable action? At @MidbrainAI , our longer-term goal is agents that apply what they remember, adapt when instructions change, and learn from corrections. Understanding where they fail today helps us decide what to test next.

Most failures in our DolphinBench run came after the facts reached the model. 89.1%: right tool, facts in context, response omitted a requirement. 7.9%: retrieval misses. 3.0%: expected tool never called.

Post attachment