Sam Alba (@sam_alba) profile picture

Engineering @anthropicai — 2x YC Founder, ex-Docker

SF Bay Area, California
Joined April 2009
Photo by Sam Alba (@sam_alba)Photo by Sam Alba (@sam_alba)Photo by Sam Alba (@sam_alba)Photo by Sam Alba (@sam_alba)Photo by Sam Alba (@sam_alba)Photo by Sam Alba (@sam_alba)Photo by Sam Alba (@sam_alba)Photo by Sam Alba (@sam_alba)Photo by Sam Alba (@sam_alba)Photo by Sam Alba (@sam_alba)
Sam Alba retweeted
Anthropic rewrote its Messages API in Rust. Zero Rust devs on the team. Claude wrote the code. Humans wrote the plan and checked old vs new matched on real traffic. CPU dropped 40-50%. Pretty sure "never do the big rewrite" is dead advice. @katelyn_lesse on @latentspacepod
105
234
134
2,991
738,281
software engineers are going to have to tackle a new set of problems to unlock powerful multiagent systems to solve the world's hardest problems - right now is one of the most interesting moments in history to be an engineer.
196
558
118
4,512
727,863
Sam Alba retweeted
there are cathedrals everywhere for those with the eyes to see ps. we are hiring and are actively trying to solve these problems
software engineers are going to have to tackle a new set of problems to unlock powerful multiagent systems to solve the world's hardest problems - right now is one of the most interesting moments in history to be an engineer.
6
7
1
347
30,362
CI needs to shift left. If you have to push to execute CI you're wasting your agents time. CI is absolutely killing my productivity right now. Traditional CI can not run at agent speed.
Announcing Dagger 1.0 beta. Replace Jenkins and GitHub Actions with CI that matches the speed and scale of coding agents without wasting compute or tokens. Featuring: test-native CI, dev shells, local and remote execution, official modules, and more. dagger.io/blog/dagger-10-bet…
32
19
6
348
31,236
Congrats @solomonstre and Dagger team, big milestone!
Announcing Dagger 1.0 beta. Replace Jenkins and GitHub Actions with CI that matches the speed and scale of coding agents without wasting compute or tokens. Featuring: test-native CI, dev shells, local and remote execution, official modules, and more. dagger.io/blog/dagger-10-bet…
14
1,578
Sam Alba retweeted
We're donating Agent Skills to the Agentic AI Foundation (@AgenticAIFdn), the same foundation we donated MCP to. Since December 2025, 70+ agent platforms have integrated the standard, including ChatGPT, Cursor, GitHub Copilot, and VS Code. Here's what that means for you:
303
422
258
8,728
999,785
handling breaking api changes at the same time as new model behaviors can be a lot of work in the way of your product taking full advantage of a new model. so we’re going to lean more on versioning to make it easier to get ahead of api changes before models require them
API version 2026-10-21 is now available. The Claude API has evolved a lot, but this is our first official version release since 2023. We plan to release versions more often so you can handle breaking changes before a new model requires them. 2023-06-01 is not deprecated.
3
30
3,135
Sam Alba retweeted
I could not imagine being productive without Claude Code Review. It runs on all of my PRs, and catches almost every bug before it goes it. This is a piece of the secret sauce that lets the team and I move so quickly while raising the quality bar
Code Review is now generally available for Claude Team and Enterprise plans. Reviews are now faster, catch more of the bugs that matter, and admins can pick from Quick, Standard, or Deep review levels for each repo.
355
180
36
5,042
470,024
Sam Alba retweeted
How to build automations with Claude Managed Agents: claude.dev/blog/building-eff… Deploy an agent that reads Slack/GitHub on a schedule (with credentials and memory) and posts updates. You can set it up with a Claude Code command and use the new API credits included in Max and Team.
128
283
49
3,511
323,984
Sam Alba retweeted
Mods are absolutely insane. You can now customize Claude to work and look the way you want by just prompting it. Each person works differently, so there's no reason why everyone should have an identical Claude experience. Make Claude your own, and share mods as plugins so others can try your mods too.
You can now mod Claude Code: - Change how it behaves - Customize the UI - Swap in your own features Write one with a few lines of TypeScript, or have Claude build it for you. Mods ship inside plugins, so you install them with /plugin in the CLI or desktop app. A few examples:
374
255
63
5,296
921,286
Sam Alba retweeted
Claude.dev is our new home for developers building with Claude. You'll find engineering deep dives, Claude Code and API guides, tips from the teams building Claude, and some fun easter eggs.
293
826
151
13,470
1,731,508
sam and his team are on a mission to reimagine how we @ClaudeDevs do our work. they've shared very cool demos so far and they're iterating fast. it's an amazing team to be a part of - let me or @sam_alba know if you're interested!
We're hiring at @AnthropicAI to work on what software engineering is becoming. If you build infra, dev tools, or agents, let's talk. Text me if you have my number, because that's the fastest way to reach me. Otherwise my DMs are open.
28
7
201
30,343
We're hiring at @AnthropicAI to work on what software engineering is becoming. If you build infra, dev tools, or agents, let's talk. Text me if you have my number, because that's the fastest way to reach me. Otherwise my DMs are open.
487
169
45
6,588
763,884
we've heard the feedback loud & clear - opus 5.5 writes much better than opus 5: less verbose, more direct, and it follows your style rules. @box's opus 5.5 integration is getting answers that are 40% less verbose without losing accuracy. please keep your feedback coming!
Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family. It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.
15
11
1
236
11,165
We Must Pace the Frontier: I’ve written a new essay on why the AI industry should slow down, with a three-part plan for doing so. Anthropic is unilaterally committing to the first of these steps. We’ll provide third-party evaluators with permanent, employee-level access to our systems, so that they can verify adherence to our safety measures, report on incidents, and assess models’ alignment during training. You can read the full post here: darioamodei.com/post/we-must…
10,591
16,337
11,364
87,601
77,038,286
if you work on a developer product, it’s easier than ever to dogfood your own product. it used to take a ton of effort, building integrations by hand. dogfooding leads to infinitely better dev experiences. no more excuses - you should always be dogfooding.
3
2
30
3,160
Sam Alba retweeted
Introducing the first AI workforce for hospitality. Hotel guests prefer talking to AI agents. As long as it finishes the job. We've seen it firsthand. Our agents drove higher review scores and satisfaction across over 50 million guest conversations at hotels, resorts, and vacation rentals. Conversion on bookings and upgrades go up 30%.
30
22
8
234
49,464
We wrote a short post about what we do for supply chain attacks: mendral.com/blog/supply-chai…
A package can be published to npm and pulled into your CI five minutes later. That's the attack window Dependabot-style scanners miss. Mendral's supply chain agent catches it at PR time. Typo-squatting, malware, suspicious post-install scripts, and packages under 72 hours old all get flagged before merge.
2
1
23
41,344
I've seen some teams recently relying less on CI checks and more on AI code reviews for shipping their code. There is a paradigm shift going on.
5
1
25
6,858
Automating DevOps at Mendral 👇 The product isn't self-serve yet but happy to give access if interested.
Custom agents are now available in Mendral. Build them in Slack: describe the task, iterate, turn it into an agent. Triggers: Schedule, GitHub Push/PR. A customer is already running daily CI failure triage, weekly build time reports, and CVE impact analysis on dependabot PRs.
4
8,037