Barry Zhang
@barry_zyj
Followers
3K
Following
693
Media
12
Statuses
68
Prototyper @Anthropic | ex-@Meta
New York
Joined December 2022
Multi-agent search was easy to prototype (V1 only took me a day) but incredibly complex to bring to production. Feels like building RAG in 2022: we see the promise but are still figuring out the primitives. Sharing our journey so far - hope it helps your exploration!.
New on the Anthropic Engineering blog: how we built Claude’s research capabilities using multiple agents working in parallel. We share what worked, what didn't, and the engineering challenges along the way.
18
29
543
My workflow for the past few months: .- Write a design doc (with Claude ofc).- Ask Claude to generate tests.- Verify the tests.- Let it cook.
This approach has made Sonnet the model of choice for developers worldwide. In addition to our new model, we're launching Claude Code, our first coding tool, in a limited research preview. With Claude Code, you can delegate substantial tasks to Claude—right from your terminal.
7
11
162
RT @AnthropicAI: Introducing Claude 3.7 Sonnet: our most intelligent model to date. It's a hybrid reasoning model, producing near-instant r….
0
3K
0
Success in the LLM space isn't about building the most sophisticated system. It's about building the right system for your needs. Had a lot of fun writing this with @ErikSchluntz!.
2025 will be the year of agentic systems. The pieces are falling into place: computer use, MCP, improved tool use. It's time to start thinking about building these systems. At Anthropic, we're seeing a few best practices emerge - we wrote a blog post with our findings:
12
7
115
Graph-based memory that you can customize is now open-source with MCP.
2
1
28
RT @ericsimons40: Case study on from @AnthropicAI:. - Zero to $4m ARR in 4 wks.- 100k+ of y'all using Bolt every wk….
0
84
0
RT @AnthropicAI: Introducing an upgraded Claude 3.5 Sonnet, and a new model, Claude 3.5 Haiku. We’re also introducing a new capability in b….
0
2K
0
RT @kscalelabs: K-Scale Labs just launched on @ycombinator's Launch YC!. K-Scale Labs 🤖 Open-source humanoid robots for everyone. Check the….
0
62
0
RT @EnricoShippole: @TeraflopAI is excited to help support the @caselawaccess and @HarvardLIL, in the release of over 6.6 million state and….
0
36
0
RT @normativeai: Hosting an event for our clients and leaders in compliance, financial services and law, on February 6 at @NYSE to discuss….
0
6
0
RT @jerryjliu0: How much data do you need to fine-tune GPT-3.5? . @barry_zyj et al. have a great article showing that you only need ~100 da….
0
1
0
RT @swyx: Q: What's better than Mixture of Experts?.A: Mixture of Mixture of Experts!. Introducing GodMode: the AI Chat Browser. https://t.….
0
162
0
RT @johnjnay: I founded a second AI company. We're pioneering an empirical, practical approach to AI alignment, leveraging law/policy & LL….
0
47
0
GPT-4 and Bard: energy, compute, medical, transportation, etc. Bing: same answers but here are internet articles. Claude:.- Energy, compute, medical, . - SV pivots!.- Elon Musk pivots!.- new "Cold War".- developing countries knowledge theft.- new world order.
0
0
2