Fredrik
518 posts

Fredrik
@fredeil
I’m here for tech reasons only. Currently working with F#, k8s, Rust. Supporter of open source.
Norway Bergabung Ocak 2019
484 Mengikuti222 Pengikut

This just seems like a nightmare to me. Anyone have good experience with it?
Claude@claudeai
You can now enable Claude to use your computer to complete tasks. It opens your apps, navigates your browser, fills in spreadsheets—anything you'd do sitting at your desk. Research preview in Claude Cowork and Claude Code, macOS only.
English

SSB har masse verdifull data, men er vanskelig å navigere i.
Vi har bygd MCP + skills til Claude og ChatGPT.
Brukt internt i TRY en stund, nå deler vi den videre 👇
🔗 tools.try.no/ssb-mcp
Norsk
Fredrik me-retweet
Fredrik me-retweet

🎁 Happy Friday - Opus 4.6 1M is now the default Opus model for Claude Code users on Max, Team, and Enterprise plans.
Pro and Sonnet users can opt in with /extra-usage.
Claude@claudeai
1 million context window: Now generally available for Claude Opus 4.6 and Claude Sonnet 4.6.
English

Kimi K2.5 continues to be my daily driver for all the basic stuff where I don't need PhD-level intelligence. I just need it done quickly. Running it at 200 tps through @FireworksAI_HQ within @opencode is just such a delight.
English

@CFDevelop In the new era of high cost of compute, writing backend services in Rust can probably save alot of money on big scale
English

@satyanadella i thought we agreed. no more ai features until you can go 60 days without an incident with windows
English

You don't work out to become fit.
You become someone who works out, then fitness follows.
Identity = action.
When you say "I'm someone who trains daily," you start acting that way.
When you say "I'm trying to get in shape," you quit when it gets hard.
Change your identity, change your results.
English

Wrote a cli to crawl Discord so I can get more signal out of where the pain points are. sqlite db is around 4GB, 660k messages. github.com/steipete/discr…
English

I packaged up the "autoresearch" project into a new self-contained minimal repo if people would like to play over the weekend. It's basically nanochat LLM training core stripped down to a single-GPU, one file version of ~630 lines of code, then:
- the human iterates on the prompt (.md)
- the AI agent iterates on the training code (.py)
The goal is to engineer your agents to make the fastest research progress indefinitely and without any of your own involvement. In the image, every dot is a complete LLM training run that lasts exactly 5 minutes. The agent works in an autonomous loop on a git feature branch and accumulates git commits to the training script as it finds better settings (of lower validation loss by the end) of the neural network architecture, the optimizer, all the hyperparameters, etc. You can imagine comparing the research progress of different prompts, different agents, etc.
github.com/karpathy/autor…
Part code, part sci-fi, and a pinch of psychosis :)

English
Fredrik me-retweet

Ghostty 1.3 is going to have a preview of AppleScript support. All windows, tabs, splits, terminals are exposed via AppleScript. For macOS users, this satisfies some of the most common requests: broadcast commands, automatic layouts, jump to working directory, etc. PR here: github.com/ghostty-org/gh…
I also think this is an incredibly important feature to ship early/now so agentic tools like Claude and Codex can take advantage of a scriptable Ghostty on macOS.
I still plan on a generic cross-platform scripting/plugin API (two separate things), but integrating with native features like AppleScript is entirely in scope of the Ghostty mission and like our Shortcuts integration it importantly lets you connect multiple sources since AppleScript can control multiple applications from one script.
Note I normally don't ship features so down to the wire with a release, but this one is very isolated in its impact and I'm going to explicit document it in the release notes and website as a preview since I fully expect we're going to iterate a lot on the objects and commands exposed.
From a security perspective, Apple already prompts for permission to control different applications so we're covered, but there is a master kill switch you can put in the config, too.
English











