Matt

Matt

@mattzcarey.com

ex pro windsurfer 🇲🇹 🌊 AI engineer. I work on streamlining access to large data sources, agents and retrieval - other interests in mech interp and data efficient fine-tuning.

633 followers1K following204 posts

Boss man did it!! DO’s will be the agent infra for the future.

Sunil Pai@threepointone.bsky.social

langgraph's multi agent example on a durable object - uses ALS to "share" the DO instance with tools - so it can make the "chart" call inside the server, but renders in the browser (yay websockets) - also uses @mattzcarey.com new checkpointer - the thing can run even when a browser isn't connected

in 2025: - build a cursed programming language - publish my RAG stuff as real research - build more models with zml - generate 100x more tokens

Matt@mattzcarey.com

learnt alot in 2024: ML -> transformers, finetuning data mindset AI -> search stuff, agent guardrails, evals cloudflare dev -> awesome modal labs -> containers in python Data engineering -> DAGs, lineage, access control, etl at scale Comp sci -> memory management, search algos, basics of zig

learnt alot in 2024: ML -> transformers, finetuning data mindset AI -> search stuff, agent guardrails, evals cloudflare dev -> awesome modal labs -> containers in python Data engineering -> DAGs, lineage, access control, etl at scale Comp sci -> memory management, search algos, basics of zig

We have been building something for a while at StackOne with no idea what it should be called. Google just told us. We are building an extension an extension for the whole HR tech ecosystem.

remote work hack take lunch after a long meeting and go do some exercise. come back with a clear head, knowing what to do. Nobody cares what time you take lunch anyway.

i've been building a thing 🦓 the api is coming together. the model compiled by zml I think this leans well on zml pros. One model, many backends, zero code change.

so a bit like this

Matt@mattzcarey.com

Trying to define the AI Engineer role, I just explained it to a friend on 2d axis. On the x axis we have designer to FE to BE to ML to Data Science On the y axis we have cloud to hardware AI engineer blob sits right in the middle. wip but I think this is a nice way of thinking about it.

Trying to define the AI Engineer role, I just explained it to a friend on 2d axis. On the x axis we have designer to FE to BE to ML to Data Science On the y axis we have cloud to hardware AI engineer blob sits right in the middle. wip but I think this is a nice way of thinking about it.

Streaming LLM tokens is a hype. Give it a year and peeps will just use rapid models for quick answers and the slower models for more complex work so much faff the last two years just for streamed tokens in chat. Horrible UX

EU ftw

European Commission@ec.europa.eu

It’s time for THE charger. Today, the USB-C becomes officially the common standard for charging new mobile electronic devices in the EU. It means better-charging technology, reduced e-waste, and less fuss to find the chargers you need! #DigitalEU

made a lil website for my granny. She needed some photo storage for her (soon to be an online) bookshop. Build her a nice little admin panel and it has dark mode :)

2024 - moved in with my gf ❤️ - new job at StackOne working on LLMs 🤖 - started ADD with MC - 4 events, over 1k people registered - won two hackathons with legends 🏆 - learnt to paraglide - ran a decent half marathon (1:36) Next year I wanna read more books, do some research and climb a few v6s

Repeat after me: more AI chat here more AI chat here more AI chat here more AI chat here more AI chat here more AI chat here more AI chat here more AI chat here more AI chat here more AI chat here more AI chat here more AI chat here more AI chat here more AI chat here more AI chat here

Check out the latency increase by using gpt-4o instead of a specific model tag This has to be a bug?

Matt@mattzcarey.com

Just noticed some mad inconsistencies with OpenAI model latency. Who can I tell?

If I ever stand trial I want O1 as my judge. Gemini would give me life in prison for not holding the door open for an elder but the slightest bit of contradictory evidence would have O1 singing my praises

what is the difference between AI studio and Vertex AI. Why are they different and why did I have to go to google (out of gcp) to find AI studio?

I'm a pretty big fan of how fast and cheap dynamodb is. but the devex = ropey. Literally writing entity shapes in comments not forget them. dynamodb-toolbox makes dev ex as pretty as working with best orms I KNOW is not an ORM but I'm smooth brained (@jeremydaly.com) github.com/dynamodb-too...

github.comGitHub - dynamodb-toolbox/dynamodb-toolbox: Lightweight and type-safe query builder for DynamoDB and TypeScriptLightweight and type-safe query builder for DynamoDB and TypeScript - dynamodb-toolbox/dynamodb-toolbox

Been living in London for almost 3 years, just got a water filter. Man it tastes like home I’m never going back to the sludge

I love when people think they know best online and end up arguing with the dude that built the actual thing. never gets old

probs won’t do an advent of ML today. Need a day off. I have something cooking with ZML. High performance inference in Zig. More code examples for the next few days :)

When the world wakes up to the power of evals. Tracing services gotta invest in their compute. 🙏 for the SREs

Matt@mattzcarey.com

So you've built something with AI, does it work? do you even know? Day 6 of Advent of ML is on evals and how you measure the success of your system pre and post deployment. Hope you enjoy :) mattzcarey.com/blog/advent-... #blogvent