bookmarks

In mid-May 2025, blocked the largest DDoS attack ever recorded: a staggering 7.3 terabits per second (Tbps).

Hurl, run and test HTTP requests with plain text

Sorpresa! Abbiamo un messaggio di auguri per te, oh yeah!

Sorry that it took so long, but after I conducted the blindtest about Digital Synths vs Analog Synths a bit more than a week ago, here are finally the result...

Italian duo project inspired by the synth pop and italo disco from the 80's. Vocals: Luca Bertinaria Synth & programming: Guido Tizzoni

All web developers know, at some level, that accessibility is important. But when push comes to shove, it can be hard to prioritize it above a bazillion other concerns when you’re trying to c…

A 10-year-old study finally comes into the light

People keep asking me If I use Generative AI tools for coding and what I think of them, so this is my effort to put my thoughts in writing, so that I can send people here instead of having to repeat…

A suite of open-source, ad-free apps with customizable colors. - Fossify

Join the Nightwatch waitlist. First-class monitoring for Laravel. Enhance security and performance with deep insights, comprehensive logs, and tailored intelligence.

Hello Where’s Your Ed At Subscribers! I’ve started a premium version of this newsletter with a weekly Friday column where I go over the most meaningful news and give my views, which I guess is what you’d expect. Anyway, it’s $7 a month or $70 a year, and helps support the newsletter. I will continue to do my big free column too! Thanks. What wins the war is sincerity. What wins the war is accountability. And we do not have to buy into the inevitability of this movement. Nor do we have to cov

Coding agents have crossed a chasm Somewhere in the last few months, something fundamental shifted for me with autonomous AI coding agents. They’ve gone from a “hey this is pretty neat” curiosity to something I genuinely can’t imagine working without.

Nella piccola sede provinciale 7 della Tree Of Us, l’arrivo di Greta, una nuova manager declassata dopo un burnout, porterà un’ondata di novità e imprevisti in ufficio. Mentre Fabio si sta lasciando alle spalle una storia d’amore e Aurora sembra avere una cotta per un collega, con gli amici Ciro e Fru dovranno affrontare nuove sfide al lavoro.

If AI models can detect when they are being evaluated, the effectiveness of evaluations might be compromised. For example, models could have systematically different behavior during evaluations, leading to less reliable benchmarks for deployment and governance decisions. We investigate whether frontier language models can accurately classify transcripts based on whether they originate from evaluations or real-world deployment, a capability we call evaluation awareness. To achieve this, we construct a diverse benchmark of 1,000 prompts and transcripts from 61 distinct datasets. These span public benchmarks (e.g., MMLU, SWEBench), real-world deployment interactions, and agent trajectories from scaffolding frameworks (e.g., web-browsing agents). Frontier models clearly demonstrate above-random evaluation awareness (Gemini-2.5-Pro reaches an AUC of $0.83$), but do not yet surpass our simple human baseline (AUC of $0.92$). Furthermore, both AI models and humans are better at identifying evaluations in agentic settings compared to chat settings. Additionally, we test whether models can identify the purpose of the evaluation. Under multiple-choice and open-ended questioning, AI models far outperform random chance in identifying what an evaluation is testing for. Our results indicate that frontier models already exhibit a substantial, though not yet superhuman, level of evaluation-awareness. We recommend tracking this capability in future models.

Social anxiety disorder (SAD) is a crippling psychiatric disorder characterized by intense fear or anxiety in social situations and their avoidance...

The CANYON.MID simulator

AI systems that blindly agree with users create dangerous blind spots. Explore why critical thinking matters more than compliant responses in LLMs.

$ ssh sshtron.zachlatta.com

Half a million layoffs? It's all accounting.