Matt Rickard Profile
Matt Rickard

@mattrickard

Followers
10K
Following
9K
Media
607
Statuses
5K

Working on LLMs. Before: StanfordGSB, Kubernetes @ Google, Blackstone.

Stanford, CA
Joined June 2009
Don't wanna be here? Send us removal request.
@mattrickard
Matt Rickard
4 months
RT @solomonstre: The distinction between "agent" and "tools" is arbitrary and meaningless. Architectures built on that distinction are dead….
0
10
0
@mattrickard
Matt Rickard
5 months
RT @thdxr: we are working on OpenControl - a library that uses AI to finally solve the headache of internal tooling. idea is simple - defin….
0
41
0
@mattrickard
Matt Rickard
7 months
RT @sundarpichai: Introducing Veo 2, our new, state-of-the-art video model (with better understanding of real-world physics & movement, up….
0
1K
0
@mattrickard
Matt Rickard
8 months
RT @Ahmad_Al_Dahle: Introducing Llama 3.3 – a new 70B model that delivers the performance of our 405B model but is easier & more cost-effic….
0
475
0
@mattrickard
Matt Rickard
8 months
interesting analogy.
@alexalbert__
Alex Albert
8 months
Like LSP did for IDEs, we're building MCP as an open standard for LLM integrations. Build your own servers, contribute to the protocol, and help shape the future of AI integrations:
0
0
6
@mattrickard
Matt Rickard
8 months
Interesting approaches on making structured generation more efficient.
@yi_xin_dong
Yixin Dong
8 months
🚀✨Introducing XGrammar: a fast, flexible, and portable engine for structured generation!. 🤖Accurate JSON/grammar generation.⚡️3-10x speedup in latency.🤝Easy LLM engine integration.✅ Now in MLC-LLM, SGLang, WebLLM; vLLM & HuggingFace coming soon!.
Tweet media one
Tweet media two
0
0
4
@mattrickard
Matt Rickard
8 months
Should check this out! TS as a first class citizen.
@calcsam
Sam Bhagwat
8 months
Excited to share that @smthomas3, Abhi Aiyer and I are building Mastra, a Typescript AI framework for the next million AI developers:
Tweet media one
0
0
2
@mattrickard
Matt Rickard
8 months
happy franksgiving
Tweet media one
0
1
8
@mattrickard
Matt Rickard
8 months
RT @jeremyphoward: Wow there is a *lot* of llms.txt activity happening now. Like… a lot lot….
0
61
0
@mattrickard
Matt Rickard
8 months
my offering to the llm overlords. 491,946 tokens (all 936 of my posts).
0
0
8
@mattrickard
Matt Rickard
8 months
Tweet media one
@alexalbert__
Alex Albert
8 months
Friday docs feature drop:. You can now access all of our docs concatenated as a single plain text file that can be fed in to any LLM. Here's the url route:
Tweet media one
0
0
7
@mattrickard
Matt Rickard
9 months
RT @charliermarsh: The secret behind my productivity is that I'm almost exclusively a print-statement debugger.
0
88
0
@mattrickard
Matt Rickard
9 months
RT @mitchellh: Thanks to a couple contributors, Ghostty has built-in VCS branching characters. Kitty introduced this[1] and I think Ghostty….
0
35
0
@mattrickard
Matt Rickard
9 months
RT @paulgb: We've been shipping as an open-source project for over a year. Now you can deploy it on @JamsocketHQ as….
Tweet card summary image
github.com
A realtime CRDT-based document store, backed by S3. - jamsocket/y-sweet
0
5
0
@mattrickard
Matt Rickard
10 months
RT @irvinebroque: We built a platform to run containers across Cloudflare’s network. It’s different. It’s schedules workloads globally — y….
0
31
0
@mattrickard
Matt Rickard
11 months
tired of writing Dockerfiles so I built dacc (docker-as-code compiler): . a TypeScript library to programmatically define an arbitrary build graph and natively build it with docker build -f. - merge parallel steps / diff layer output.- nested builds.- cache-efficient.- as-code
Tweet media one
3
3
19
@mattrickard
Matt Rickard
1 year
Nice! Structured output is important. Cool to see this deployed at scale.
@romainhuet
Romain Huet
1 year
Introducing Structured Outputs! A huge leap beyond JSON mode, solving a major challenge for developers. If your app relies on a specific JSON format to drive the UI, our models now match your schema—every time. No more missing keys or hallucinated enums!.
1
0
6
@mattrickard
Matt Rickard
1 year
RT @AIatMeta: Introducing Meta Llama 3: the most capable openly available LLM to date. Today we’re releasing 8B & 70B models that deliver….
0
1K
0
@mattrickard
Matt Rickard
1 year
RT @alighodsi: Today we released an open source model, DBRX, that beats all previous open source models on the standard benchmarks. The mod….
0
210
0