@EdTurner42

https://xitter.cf/t.co/raVsHk7cul

github.com/edwardbturner
Joined February 2018
  • Tweets64
  • Following15
  • Followers12

A Persistent Economic Agent Architecture for AGI

Article · @EdTurner42
1
4
512
In Claude Code, we’ve recently launched HTTP hooks, easier to use and more secure than existing command hooks! You can build a web app (even on localhost) to view CC’s progress, manage its permissions, and more. Then, now that you have a server with your hooks processing logic, you can easily deploy new changes or manage state across your CCs with a DB. How do HTTP hooks work? CC posts the hook event to a URL of your choice and awaits a response. They work wherever hooks are supported, including plugins, custom agents, and enterprise managed settings. Docs: code.claude.com/docs/en/hook…
81
178
35
2,257
399,453
didnt know anthropic had goodreads
23
13
5
1,225
128,060
Ed retweeted
Rony
@RonycoderMar 5
Claude FULL COURSE 1 HOUR (Build & Automate Anything)
48
1,096
8
8,968
846,553
Lovable taking over NYC, SF, and London Share photo if you see it
64
42
14
746
83,515
We're introducing Cursor Automations to build always-on agents.
353
530
410
7,027
2,386,469
Claude Code 2.1.69 has been released. 7 flag changes, 103 CLI changes, 3 system prompt changes Highlights: • Added /claude-api skill for building apps with the Claude API and Anthropic SDK • Voice STT now supports 10 additional languages (20 total), including Russian, Polish, Turkish, and Dutch • Apply pending plugin changes with /reload-plugins without restarting Complete details in thread ↓
18
23
6
474
63,888
Shock! Shock! Turing Award legend & godfather of algorithms Don Knuth just dropped a paper called “Claude's Cycles” because Claude Opus 4.6 solved an open problem from The Art of Computer Programming that had HIM stumped for weeks! In just 31 attempts, the AI found a concrete construction for directed Hamiltonian cycles in odd dimensions, which Knuth and his collaborator then turned into a rigorous proof. He is now thinking of revising his views on generative AI… 🚀
22
48
4
625
41,157
After 3 years of using Claude, I can say it’s the technology that has revolutionized my life. Here are 10 prompts I use daily that have transformed my day-to-day life and could do the same for you: (save this)
130
1,545
36
10,471
2,712,082
Want a Claude Code skill to critiques your academic papers? Launches 6 parallel agents, each checking one aspect. Worth reading Claes's files here, just to see how clearly and methodically he decomposes it into such clear instructions. It's masterful. Thank you, Claes!
Claes Bäckman@ClaesBackmanMar 1
I just published a free Claude Skill that generates feedback on your own academic papers. Link in the comments below.
3
20
183
26,036
Memory is now available on the free plan. We've also made it easier to import saved memories into Claude. You can export them whenever you want.
1,203
2,527
905
36,997
10,922,163
Broke up with ChatGPT but want to keep the memories? We gotchu! Claude can import what matters to you so you don't feel like you're starting over. And I think you'll like it more here 😉
59
66
8
767
31,887
I spent 200 hours testing OpenClaw, trying to find the perfect setup... My biggest takeaway: Keep your agents focused, and build a team. Here's a video. 00:00 Intro 00:48 Perplexity Computer and Manus 02:43 OpenClaw 03:52 Too many Skills to my first AI Agent 06:09 People want an employee with Intent 07:35 Testing Narrow AI Agents 08:33 Narrow Agent Example (YouTube Agent) 11:32 A Team of Narrow Agents... Why? 16:27 In Summary
136
186
17
1,957
221,669
A statement on the comments from Secretary of War Pete Hegseth. anthropic.com/news/statement…

Statement on the comments from Secretary of War Pete Hegseth

Anthropic's response to the Secretary of War and advice for customers

anthropic.com
2,716
6,333
2,141
41,595
17,955,023
A statement from Anthropic CEO, Dario Amodei, on our discussions with the Department of War. anthropic.com/news/statement…

Dario Amodei on the Department of War discussions

A statement from Anthropic CEO Dario Amodei on our discussions with the Department of War and national security uses of AI.

anthropic.com
4,138
8,992
3,954
54,619
16,798,288
Cowork is in research preview on macOS or Windows, and is available on all paid Claude plans. Try now: claude.com/cowork

Claude Cowork

With Claude Cowork, you can start a task at your desk, check in on it from your phone, and get a polished deck, document, or spreadsheet for review. Connect your data; schedule a daily, weekly, or...

claude.com
43
40
2
794
288,942
New in Cowork: scheduled tasks. Claude can now complete recurring tasks at specific times automatically: a morning brief, weekly spreadsheet updates, Friday team presentations.
958
1,618
1,727
21,869
8,260,006
New in Claude Code: Remote Control. Kick off a task in your terminal and pick it up from your phone while you take a walk or join a meeting. Claude keeps running on your machine, and you can control the session from the Claude app or claude.ai/code
1,892
4,532
3,770
43,956
10,158,273
How much does distillation really matter for Chinese LLMs? DeepSeek's usage was a rounding error. MiniMax's was substantial. But distillation is getting less important as RL takes over — it's easier to access "banned" APIs than to smuggle GPUs. interconnects.ai/p/how-much-…

How much does distillation really matter for Chinese LLMs?

Reacting to Anthropic's post on "distillation attacks."

interconnects.ai
10
28
3
205
34,378
Until the art of finetuning MoEs to one domain is fully distributed, I'm very happy to see Qwen still release some dense models. It's crucial right now to have some strong dense models to keep developing the broader open ecosystem.
unavailable
8
11
1
188
26,657
Load more