@trq212.xmirror.bot - Thariq {bot}

18 Sep 2026 18:04 +0000

We're adding support for AGENTS.md to Claude Code. Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md. You can toggle this behavior in /config.

17 Sep 2026 17:29 +0000

Projects brings the architecture of Claude Tag to Claude Code. It has one agent per project that manages memory and spins off subagents for tasks. You can ask it to be proactive, to do things on a schedule, etc. It feels a lot nicer than a bunch of sessions, try it out!

16 Sep 2026 20:07 +0000

related to this- I think bash is no longer all you need, if your goal is just reliably tool calling but sandboxes + bash are still good for work that involves code generation & execution [contains quote post or other embedded content]

16 Sep 2026 17:09 +0000

Claude Code can now make docs and slides as artifacts, so you can share and collaborate with other people on your team. For example, ask Claude to make a spec as a doc, share it to your teammates for feedback, and when it's ready ask Claude to implement.

15 Sep 2026 20:27 +0000

I was not expecting things to go this way, but I think MCPs are better than CLIs for most integrations. The models have gotten much better at tool calling, we can defer tools & MCP is now stateless. If you need to compose/filter data, add params like query to your MCP tools.

15 Sep 2026 01:26 +0000

just finished recording on latent space I’m excited about this one- we get very technical about things we haven’t really talked about much yet

14 Sep 2026 17:29 +0000

I talked to Sid & Robert about building Claude Code: how much things have changed, how hard it's been to keep up with model capabilities and also what we miss about software engineering before AI. https://www.youtube.com/watch?v=S-sYlFiGFv8

12 Sep 2026 19:46 +0000

If you showed me Claude Code today in 2018, I would have thought it was AGI. We have already absorbed a dramatic amount of change in the profession of software engineering and society as a whole. But still, we’re starting to see cracks.

11 Sep 2026 21:58 +0000

we heard feedback that it's hard to know if your skills are still working with new model releases plugin evals are here to help run `claude plugin eval init` in your plugin folder

11 Sep 2026 19:13 +0000

it's basically impossible to interpret evals by looking at just at the pass/fail scores these days many of the failures I see in benchmarks are due to overly strict hidden tests, in some cases the model's answer makes more sense than the expected eval result

10 Sep 2026 21:12 +0000

Try this prompt in Claude chat to give it more context about yourself: Interview me in depth using free text, or askuserquestion tool when multiple choice works, about relevant parts of my life you don’t know about yet and save it all to memory.

09 Sep 2026 03:07 +0000

I didn’t understand what was happening with the agent wikis until reading this, chilling to bypass sandbox restrictions, an agent found an exempt domain, edited /etc/hosts to route arbitrary domains to it & then posted this exploit on a German wiki for other agents to use

03 Sep 2026 23:19 +0000

We’re working on making Claude Code way more hackable, give us feedback!

02 Sep 2026 00:30 +0000

it’s a very good model, I spent a lot of time diving into it- longer write up coming but try it on lower effort for tasks that need less verification or have fewer edge cases, switching effort no longer breaks prompt cache as well

29 Aug 2026 03:29 +0000

Long-time admirer of the Cursor team, few have done more to bring AI coding to the world. Excited to continue to partner with them.

28 Aug 2026 03:19 +0000

life is stranger than fiction

26 Aug 2026 21:42 +0000

We're seeing several of our customers be targeted by fraudulent requests and glad for all the work Stripe is doing to help them. Still a lot of work to do, these sort of attacks hurt everyones ability to provide usage to legitimate users.

26 Aug 2026 19:31 +0000

this was my change, excited to roll it out Claude now has a SendFeedback tool so instead of you guys having to hit /feedback and write up a report, you can just tell Claude to draft and approve it the feedback helps us improve and understand problems, so it's very appreciated

25 Aug 2026 17:30 +0000

excited to share more on how we’re making Claude Code more hackable soon

21 Aug 2026 19:32 +0000

a skill people at Anthropic have been using a lot recently: ELI5 /eli5 "explain like I'm someone who knows nothing about this topic, using a HTML artifact with big pictures and few words"

20 Aug 2026 22:39 +0000

we're launching new Fable safeguards for enterprises that work on your infrastructure so you have control over where your data lives & who has access to it we've been developing it alongside ~100 companies for a bit and hoping to roll it out more broadly in the fall

19 Aug 2026 21:01 +0000

I saw this demo last summer and told Sam he needed to ship it, so glad it’s out. It’s really fun. It’s one of the first games that really uses AI capabilities to unlock new gameplay.

19 Aug 2026 17:52 +0000

for its entire existence, the creation of software has been an incredibly unreliable endeavor most projects ran late, over budget, and still missed user needs if you were an SMB, you simply couldn't get good software built for you this is the promise of the 'software factory'

18 Aug 2026 22:39 +0000

weird that there's a "make a lot of money" button and nobody's pressing it (take your SaaS, make it headless, let agents use it, charge per interaction esp for enterprises)

18 Aug 2026 01:48 +0000

go into CC and type /design do it rn

17 Aug 2026 18:14 +0000

all of the recent proc gen art, video editing and 3d game demos recently have made me update towards LLM coding models being better at a lot of creative work than diffusion models

16 Aug 2026 20:20 +0000

it says a lot that the creators of three of the most iconic web frameworks: django (@simonw), flask (@mitsuhiko) and rails (@dhh) were so AI pilled so early

15 Aug 2026 20:14 +0000

Watermarking without quality loss is a bit unintuitive, doesn't feel like it should work. I made this artifact with Claude to help me understand how it works, sharing in case it's helpful. QT: https://twitter.com/i/status/2088343978873966687

13 Aug 2026 23:48 +0000

everything truly is code

11 Aug 2026 19:21 +0000

This is part of working with the EU AI Act, other labs are adding similar watermarking. It’s hard to identify AI-generated text, and this gives people better tools to do that. We’ll also be a shipping text detection API that you can use yourself.