Rickard Nilsson (@rickardn) header
Rickard Nilsson (@rickardn) profile picture

Developer @ninetech

Karlstad, Sweden
Joined August 2008
Photo by Rickard Nilsson (@rickardn)Photo by Rickard Nilsson (@rickardn)Photo by Rickard Nilsson (@rickardn)Photo by Rickard Nilsson (@rickardn)Photo by Rickard Nilsson (@rickardn)Photo by Rickard Nilsson (@rickardn)Photo by Rickard Nilsson (@rickardn)Photo by Rickard Nilsson (@rickardn)Photo by Rickard Nilsson (@rickardn)Photo by Rickard Nilsson (@rickardn)
Built an agent dashboard for all my agents, sub agents and background agents. Each room is a team room. When an agent need my attention it raises its hand #antfarm #ai
1
1
115
Rickard Nilsson retweeted
Fable 5 is the biggest step up I’ve felt in our models since Opus 4.5 back in November. After 4.5 came out I uninstalled my IDE when I realized that I’d been doing 100% of my coding in a terminal for a few weeks. With Fable, it’s felt like Claude has stepped up from being a coding agent to a thought and design partner in building the product. Fable has judgement, taste, and dimensionality in a way that previous models didn’t, leading me to trust it more with the most complex work. I think the first time I had this realization was when I asked Fable to debug something. It is the first model I have used that was so methodical and precise, taking measurements and adding logs then verifying that it truly fixed the issue before declaring victory. There’s nothing in claude code’s prompting telling the model to do that, it’s just part of its personality. It really has this “big model smell” that I haven’t felt before.
631
597
167
10,547
922,319
Rickard Nilsson retweeted
Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Its capabilities exceed those of any model we’ve ever made generally available.
4,907
14,056
9,953
103,192
57,744,901
Rickard Nilsson retweeted
Claude Code's first demo got two Slack reactions. One year after GA, @bcherny and @_catwu look back: verification best practices, why we built auto mode, routines and loops, and what's next. youtube.com/watch?v=Hth_tLaC…
59
81
24
1,147
656,742
Rickard Nilsson retweeted
Seeing a number of benchmarks showing Opus is the best model for long-running work. Five tips for running Opus autonomously for hours/days: 1. Use auto mode for permissions, so Claude doesn’t ask for approval 2. Use dynamic workflows, to have Claude orchestrate hundreds/thousands of agents to get a task done 3. Use /goal or /loop, to nudge Claude to keep going until it’s done 4. Use Claude Code in the cloud, so you can close your laptop (easiest way is the desktop or mobile app) 5. Make sure Claude has a way to self-verify its work end to end: Claude in Chrome browser extension for web, iOS/Android sim MCP for mobile, a way to start the full web server or service for backend work
Can coding agents stay coherent over a 1 billion token budget? Can they build Slack from scratch? Rewrite a JAX codebase in PyTorch? Build a C compiler in Rust? Enter SWE-Marathon: a benchmark for autonomous long-horizon software work.
303
276
90
3,467
667,238
Rickard Nilsson retweeted
Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors. Available today at the same price.
3,587
8,290
5,298
65,977
15,521,814
Rickard Nilsson retweeted
karpathy's CLAUDE.md hit #1 on github trending. 220,000 stars. most devs still haven't read it. it's 65 lines. it took AI coding accuracy from 65% to 94%. the 4 rules inside: → think before coding state your assumptions. ask when unsure. never guess. → simplicity first write the minimum code that solves the problem. no abstractions nobody asked for. → surgical changes don't touch code unrelated to the request. every changed line must trace back to what was asked. → goal-driven execution turn vague instructions into verifiable success criteria before writing a single line. that's it. 65 lines. 4 rules. 94% accuracy. save this before everyone else does.
148
681
48
7,915
2,641,154
Rickard Nilsson retweeted
In the next version of Claude Code: run /usage to see a breakdown of which Skills, Agents, MCPs, and Plugins are using your tokens CLI today, coming to Desktop next
327
362
78
5,327
291,494
Rickard Nilsson retweeted
The best way to level up from 1 agent => many agents. No more cycling between terminal tabs
New in Claude Code: agent view. One list of all your sessions, available today as a research preview.
220
207
32
4,987
514,764
Rickard Nilsson retweeted
New in Claude Code: agent view. One list of all your sessions, available today as a research preview.
975
2,041
997
28,304
6,423,888
Rickard Nilsson retweeted
Claude for Excel, PowerPoint, and Word are now generally available, and Claude for Outlook is in public beta. As Claude moves between your Microsoft apps, it carries the full context of your conversation.
1,087
3,966
1,446
47,509
28,271,029
Rickard Nilsson retweeted
Effective today, we are: 1) Doubling Claude Code’s 5-hour rate limits for Pro, Max, and Team plans; 2) Removing the peak hours limit reduction on Claude Code for Pro and Max plans; and 3) Substantially raising our API rate limits for Opus models.
1,205
3,822
2,491
43,677
9,173,470
Rickard Nilsson retweeted
Code with Claude is happening now! ▪︎ 9:00AM - Keynote ▪︎ 10:30AM - What's new in Claude Code ▪︎ 11:15AM - Building on Claude at GitHub scale ▪︎ 12:00PM - Get to production faster with Managed Agents All times PT. nitter.cf/i/broadcasts/1qGoNegbn…
215
631
124
5,305
837,151
Rickard Nilsson retweeted
An awesome regex visualization tool regex-vis.com
27
525
11
4,326
278,120
Many call AI "a junior dev on your team." 20 years as an architect. One month with Claude Code at fleet scale. This is what it looks like when you actually drive it like a senior 👇
5
48
Five repos through git-flow release in one coordinated arc. Docs and onboarding guides written alongside the code, not after.
25