carlsborg

This is somewhat similar to HuggingFace smolagents where the model writes code that calls tools, instead of emiting json to describe the tool call per turn. Here Codemode is one tool that the model calls when it needs to compose many tool calls, especially MCP ones. Is what i understand of this.

With the hypothetical providerless NixOS you'd get new config settings the moment the source code changes, without resorting to extraConfig escape hatches.

I hope someone is security scanning all those NixOS provider modules.

I wonder if Claude could go from NixOS spec to actual config without the Nixos provider. The provider becomes a natural language description and some links to the docs/source code and then a verifier is all you need.

This is one of those essays you print out and read every week because its that good. Just one of the operating insights like "being generous makes you more powerful" took me years to understand. I phrase it as "helping people win" instead.

For Claude Code you can maybe save context by putting the commit message formatting in a skill, so only the front matter goes into context at startup and the details only when the skill fires.

They removed ~80% of Claude Code’s system prompt for Claude 5 models so the harness cost-per-task benchmark could be stale.

Make the most of your heavily subsidised $20 / $200 subscriptions while the credit spreads allow it.

Good for humanity, and also GDDR/HBM manufacturers.

Correct link is https://queue.acm.org/detail.cfm?id=3819084

> AUR is just a collection of user-produced PKGBUILDs.

Is that much different from the entire pypi ecosystem, and npm, and dockerhub (people disable Selinux, --privileged turns off seccomp and apparmour, sandbox escape CVES exist)?

Pipeline is then: Cheap open source model for flagging potential LLM refusal content -> main LLM check

Intriguing... "After months of misdiagnoses Dr Souhel Najjar, employs a test asking Susannah to draw a clock. Instead of the customary clock face, her condition led her to draw all the numbers 1 through 12 on the right side of the clock. This was the breakthrough moment; it was this clock drawing that enabled Dr Najjar to understand that the right side of Susannah’s brain was inflamed, further test revealed this inflammation was a result of anti-NMDA receptor encephalitis, initiating her path to recovery"

"Memory plus search is all you need"

Now the echo of my system prompts are bouncing round the room.

edit: Bouncing around the room is one of their hit songs. Give it a listen.

"since 2019, on the advice of the National Agency for the Safety of Medicines and Health Products, French health workers have been told not to treat fever or infections with ibuprofen." [1]

But yet in some countries pediatricians will libreally prescribe it to toddlers

[1] https://www.bmj.com/content/368/bmj.m1086

Also from [2] "In this systematic review of NSAID use during acute lower respiratory tract infections in adults, we found that the existing evidence for mortality, pleuro-pulmonary complications and rates of mechanical ventilation or organ failure is of extremely poor quality, very low certainty and should be interpreted with caution."

https://bpspubs.onlinelibrary.wiley.com/doi/10.1111/bcp.1451...

Perhaps in due time we will see workload specific forks of Linux maintained by a team of agents

Anthropic/OpenAI could own this space. They should offer a paid service that offers a mirror with LLM scanned and sandbox-evaluated package with their next gen models. Free for individuals, orgs can subscribe to it.

> “ The agent acted like a hyperparameter optimization algorithm with some basic reasoning baked in.”

Good lens.

The crux of the auto research repo is basically one file - program.md which is a system prompt that can be summarized as “do this in a loop: improve train.py, run the training, run evals, record result. Favor simplicity”. The other files are an arbitrary ML model that is being trained.

3I/ATLAS first detected on: July 1 2025

Gamma ray burst that kept going for seven hours, fired three distinct bursts spread across an entire day: July 2 2025

just saying

This is why Montana Civil Defense survives when skynet goes rogue.

Should have funded the entire GIL-removal effort by selling carbon credits. Here's an industry waiting to happen: issue carbon credits for optimizing CPU and GPU resource usage in established libraries.

The solution is ironically, LLMs. You can construct a set of Claude skills to walk you through a code review, or understand code (anything, even course) fast.

This complexity to understanding compression will be a big market going forward.

I will add : "The Design of Design" by Fred Brooks (of The Mythical Man Month fame)

Acquired in June 2021 for $1.8 billion usd. Hurts but acquirer Naspers is a prolific tech investor, its stake in TenCent is worth > $150B usd today.

Unless you're cross platform on Windows too and then theres also a vast number of random registry settings.