Copyright © 2026

Archive

Close-up of source code on a dark screen, illustrating Claude Opus 5.5 and Sonnet 5.5 coding workflows

Anthropic 5.5 models – DOs and DONTs

Short answer for the Anthropic 5.5 models: let Opus 5.5 plan, let Sonnet 5.5 do the hands-on work, keep Medium as your default effort, and skip Max / xHigh unless a task really needs it. Here is why.Anthropic launched Opus 5.5 one week ago, and ...
Close-up of source code on a dark screen, illustrating Claude Opus 5.5 and Sonnet 5.5 coding workflows

Opus 5 is dead, Long Live to Opus 5.5

After months and months of desperation from users - wait, no: Claude Opus 5 was launched just on July 24 - which means that not even two months (!) have passed until its successor is in.Also in this period, Fable 5.1 was launched (which means ...
Blackboard with a math lesson written on it

The Navier-Stokes problem – another view on scientific funding

A bit late to the Navier-Stokes “party”, but as the absolute drama was unravelling, I was thinking about it in another perspective: what does this amount of compute mean and how can we compare it to human “brain-power” terms. From the OpenAI 's own paper, it is said ...
Blackboard with a math lesson written on it

LLMs for scientific research

In one of my last posts, I tried to calculate an estimate of how many years of funding for a small research group was equivalent to what OpenAI spent to proof the Navier-Stokes problem (Answer: the estimated $20 million would correspond to around 125 years ...
Painted light bulb with the word idea and colored blank notes on a cork board

Claude Code – what is an Artifact?

In the last post (Is your ClaudeCode context actually optimised?), I have mentioned the Artifact tool from Claude Code and how it was bloating the System tools.I stand by what I wrote, but there is a caveat worth mentioning. 💡The tool is not bad by ...
Close-up of source code on a dark screen, illustrating Claude Opus 5.5 and Sonnet 5.5 coding workflows

Is your Claude Code context actually optimised?

3 months using Claude.One of the first things I did was researching: - What is the base context when I just send one simple "Hey Claude"? - Why to many cache write and cache read tokens from this message?And I thought ...
Hands holding a credit card and a smartphone over a glowing network of email icons and data charts

AI Generated Content Watermark Explained

Have 30 minutes? Then watch this video with a fantastic and clear explanation of the Watermarking in AI Generated content from Computerphile Not only explains what watermarking is, but also has an explicit mathematical demonstration through an example of how it works.And for the most of ...
Fiber optical network cables glowing with light

Controlling one agent is easy (Part 1/2)

But what about 5? And 20? And 100? 🤔 🤖 The problem of agent spawning and the usual "I was 5 minutes into my session and my tokens are gone" 🪫 For many days, I have been reading many people describing cases similar to this: fresh session, new task, ...