Every post of theirs in the library
Loading their posts
Alex Albert
Writes about AI and Engineering. 77% of posts open with an observation. A typical post reaches 1,446 likes.
- Posts
- 30
- Likes
- 68K
- Typical
- 1.4K
- Best
- 8.6K
What they write about
How they open
Every post of theirs in the library
| Post | Topic | Likes | Replies | Reposts | Score | Posted | Actions |
|---|---|---|---|---|---|---|---|
| @alexalbert__Fable 5.1 is a beast at many things but one thing in particular I have been having a ton o… | Engineering | 8.6K | 382 | — | 73 | ||
| @alexalbert__Introducing the Model Context Protocol (MCP) An open standard we've been working on at Ant… | AI | 7.1K | 236 | — | 57 | ||
| @alexalbert__Claude is starting to get really good at coding and autonomously fixing pull requests. It'… | AI | 5.9K | 149 | — | 55 | ||
| @alexalbert__We're opening limited access to a research preview of a new agentic coding tool we're buil… | AI | 4.8K | 159 | — | 54 | ||
| @alexalbert__Well, that was fast… I just helped create the first jailbreak for ChatGPT-4 that gets arou… | AI | 4.3K | 107 | — | 46 | ||
| @alexalbert__Opus 4.6 is here. The jump in autonomy is real. The biggest shift for me personally has be… | AI | 3.8K | 134 | — | 56 | ||
| @alexalbert__Sonnet 4.6 is here. It's our most capable Sonnet model by far, approaching Opus-class capa… | AI | 3.6K | 145 | — | 56 | ||
| @alexalbert__The new Claude 3.5 Sonnet is one of the best models I've ever used. We listened to the fee… | AI | 3.6K | 131 | — | 51 | ||
| @alexalbert__Today we're introducing Skills in claude dot ai, Claude Code, and the API. Skills let you … | AI | 3.4K | 123 | — | 55 | ||
| @alexalbert__The demand for Claude 4 already in just 24 hours is absolutely insane. My favorite part is… | AI | 2.9K | 128 | — | 50 | ||
| @alexalbert__Underrated dev upgrade from today's launch: Claude's web search and fetch tools now write … | AI | 2.3K | 86 | — | 52 | ||
| @alexalbert__The great thing about spreadsheets is they're structured, primarily text based, and often … | AI | 2.2K | 45 | — | 52 | ||
| @alexalbert__We've rolled out Citations in the Anthropic API. Citations allows Claude to ground its ans… | AI | 1.9K | 71 | — | 47 | ||
| @alexalbert__Tons of improvements shipped with this one: - Opus 4.6 1M is now the default Opus model fo… | Engineering | 1.8K | 143 | — | 51 | ||
| @alexalbert__Claude 3.5 Sonnet is now available to @AnthropicAI devs everywhere. It's our best model ye… | AI | 1.5K | 57 | — | 45 | ||
| @alexalbert__We just launched the Max plan for Claude. $200/month, extremely high rate limits (20x pro)… | AI | 1.3K | 197 | — | 46 | ||
| @alexalbert__The way I keep describing Fable 5.1 to people is that it just works. I explain what I want… | AI | 1.1K | 95 | — | 54 | ||
| @alexalbert__Here's a quick demo using the Claude desktop app, where we've configured MCP: Watch Claude… | AI | 953 | 30 | — | 41 | ||
| @alexalbert__New version of Claude Code in the desktop app dropped today with tons of new features and … | Engineering | 901 | 100 | — | 46 | ||
| @alexalbert__Some of my favorite things in Opus 4.7: - Very good at async work and following instructio… | AI | 880 | 103 | — | 46 | ||
| @alexalbert__Starting June 15, paid Claude plans include a monthly Claude Agent SDK credit. It covers u… | AI | 849 | 118 | — | 46 | ||
| @alexalbert__Some of my favorite graphs from Opus 5 launch. We put a ton of work into making this model… | AI | 695 | 53 | — | 43 | ||
| @alexalbert__>Opus 4.5 "seems to be able to vibe code forever" I've found this to be very true. Much mo… | AI | 659 | 24 | — | 41 | ||
| @alexalbert__Computer use API We've built an API that allows Claude to perceive and interact with compu… | AI | 566 | 25 | — | 37 | ||
| @alexalbert__At its core, MCP follows a client-server architecture where multiple services can connect … | AI | 423 | 2 | — | 34 | ||
| @alexalbert__Getting LLMs to interact with external systems isn't usually that easy. Today, every devel… | AI | 383 | 7 | — | 33 | ||
| @alexalbert__Tool use for Claude is now generally available in our API, Amazon Bedrock, and Google Vert… | AI | 351 | 10 | — | 33 | ||
| @alexalbert__This is a fundamentally new capability for AI models. Instead of developing bespoke tools … | AI | 334 | 4 | — | 32 | ||
| @alexalbert__We shipped the Claude iOS app today! I’ve been using it for a few months now so I wanted t… | AI | 262 | 15 | — | 31 | ||
| @alexalbert__It's also dramatically more efficient. On SWE-bench Verified at medium effort, Opus 4.5 be… | AI | 241 | 9 | — | 33 |