Sheinbaum rassicura, 'il trattato commerciale nordamericano non è a rischio'

OpenStation Blog: I Deleted 168,000 Lines of Comments. My AI Agent Didn’t Notice
by Roberto Aranda on Ottobre 13, 2026 at 5:58 pm
Almost a third of our source code was comments. I deleted all of them and asked an AI agent to build the same features on both versions of the codebase, three times each. The code it wrote was just as good with or without comments. If you use agents on a real codebase and wonder whether comments help them, slow them down, or don’t matter, here’s what I found. Why I tried this In this video (around 23:07), Lauren mentions that they don’t let their agents write comments in the code. Our codebase, is the opposite: it’s full of comments, and most of them were written by agents. So I wondered: are all those comments helping the agent, or are they just extra text it has to read? The experiment in one paragraph I made a copy of the codebase with every comment removed, about 168,000 lines in total. Then I gave the same task to the same agent on both copies, three times on each, and checked the results the same way. I did this for two tasks, a small one and a bigger one. The results Every run passed every check: lint, type checks and the existing tests, plus, on the bigger task, a hidden test the agent never saw. A separate AI judge scored each result without knowing which copy it came from (more on that below). Small task: tile all open windows (score out of 19) BranchScoreTokensCostWith comments18.32.18M$1.42Without19.01.71M$1.04 Bigger task: keep a window on top (score out of 23) BranchScoreTokensCostWith comments21.79.06M$3.84Without22.09.12M$3.95 The numbers are averages of three runs. The score differences are within noise, and so is the cost on the bigger task. On the small task, the agent used about 22% fewer tokens without comments, which makes sense: there was simply less to read. The bigger task had a trap. The pinned state has to survive a page reload, and the PHP function that saves the window session drops any key it doesn’t know. Miss it and the feature looks fine until you reload. That’s exactly the kind of thing you’d expect a comment to help with. All six runs found it, with and without comments. Why one run is not enough My first plan was to run each branch once. I’m glad I didn’t. On the bigger task, the three runs with comments used 8.21M, 8.79M and 10.17M tokens. The three runs without comments used 7.01M, 9.70M and 10.64M. If I had picked one run from each branch, I could have written two opposite blog posts. Comparing 10.64M with 8.21M, removing comments makes the agent 30% more expensive. Comparing 7.01M with 10.17M, it makes the agent 31% cheaper. Same task, same code, same day. Agents are not deterministic. If you’re measuring one, run it more than once. How I ran it The agent: Claude Code with Opus 5.5 at high effort. Same model and settings for every run. The two codebases: our main branch, and a copy with the comments removed. I compiled both and checked that the resulting code is identical. The only comments left are the ones the tools need to work, such as lint directives and plugin headers, about 800 lines. The tasks: two real features, with the same prompt on both branches. The checks: the project’s own lint, type checks and tests. On the bigger task, also a hidden test I added after the agent finished, so it couldn’t write code just to pass it. The judge: a separate Claude session read each change and scored it against a checklist written before the runs: does it work, does it follow the project’s conventions, does it have tests, and so on. The changes were labelled with random names, so the judge didn’t know which branch each one came from. The runs: three per branch per task, alternating branches so that time of day affected both equally. My conclusion For the agent, code comments don’t make a difference to the quality of the code it writes. They don’t help, and they don’t hurt. So keep a comment or delete it based on what it does for the people reading the code, not for the agent. This doesn’t prove comments have zero effect. I tested one model, two tasks and three runs per branch, which is enough to rule out a big effect, not a small one. Next: comments made no difference, but removing our docs/ folder and AGENTS.md did. That’s the next post. Appendix: data and links The codebase with comments The codebase without comments Exactly what was removed (GitHub may only show part of it) Two of the small-task runs as pull requests: with comments, PR 974 and without comments, PR 975 Full results, all runs: results page If you want to see the experiment script and the rubrics, they are all here Lines of code, measured with scc: WithWithoutWhole repository765,491597,332Plugin source code408,527280,421Plugin source code means the code that ships in the plugin (src/, includes/, apps/ and the CSS), without tests, docs, or tooling.st
Matt: Neal Stephenson Live!
by Matt on Ottobre 13, 2026 at 3:53 pm
Speaking of sci-fi authors, Automattic is hosting Neal Stephenson for a livestream about his new book soon, please tune in! Neal was a big influence on WordPress! I got hip to him from Tantek. In the source code of billions of pages you’ll see this: <link rel="profile" href="https://gmpg.org/xfn/11"> GMPG is the Global Media Protocols Group, “an experiment in Metamemetics.” Inspired, of course, by the Global Multimedia Protocol Group that owned the virtual real estate in Snow Crash’s metaverse. Eric, Tantek, and I were reacting to the idea that there should be a separate heavily-marked-up RDF or XML web, and that HTML couldn’t be extended or enriched with metadata in a way that was beautiful to both humans and machines. It was really an aesthetic war. (It later got more built out in Microformats.) We should revisit some of those principles because the web could use more distribution right now.
Open Channels FM: Balancing AI Efficiency Costs and Value in Markdown Data and Open Source Security
by Bob Dunn on Ottobre 13, 2026 at 2:15 pm
In today's news, markdown streamlines AI input, AI-generated security reports increase workloads, and autonomous agent costs affect project efficiency
Course Platform Fees Compared: 14 Platforms to Sell a Course (+ Free Calculator)
by Harshit Arora on Ottobre 13, 2026 at 1:42 pm
We compared fees on Teachable, Kajabi, Stan, Udemy, WordPress LMS plugins, and more. Plug your own numbers into our free calculator to see the real cost! The post Course Platform Fees Compared: 14 Platforms to Sell a Course (+ Free Calculator) appeared first on Themeisle Blog.
Open Channels FM: Open Channels FM Heading to the Web Summit 2026 in Lisboa
by Bob Dunn on Ottobre 13, 2026 at 10:00 am
Next month in November, I’ll (Bob) be attending the Web Summit in Lisbon, Portugal. I have been to conferences in the past that have had attendance up to 15,000, but never one that has over 70,000 attendees. That’s a lot of people. A few months ago I applied for media creditation, unsure of their parameters

RSS di Mondo - ANSA.it Updated every day - FOR PERSONAL USE ONLY

Argentina, indetto il primo appalto per la costruzione della base militare di Ushuaia
on Ottobre 13, 2026 at 8:46 pm
Gara per il molo militare 'pubblica e nazionale' con un costo di 122 milioni di euro
Zelensky, 'raid su centrale termoelettrica a Kiev, gli alleati non ci hanno avvertito'
on Ottobre 13, 2026 at 8:38 pm
Colpito anche un palazzo di nove piani
L'Argentina celebra primi risultati accordo Ue-Mercosur, export in aumento del 21%
on Ottobre 13, 2026 at 8:16 pm
'Incremento del 44% per le vendite di prodotti con riduzioni tariffarie'
Fujimori propone 'ordine e disciplina' nelle scuole in Perù
on Ottobre 13, 2026 at 7:15 pm
Annunciata una nuova legge che vieta i capelli lunghi ai ragazzi e il trucco alle ragazze
Forti esplosioni udite a Riad e nei pressi di un impianto Aramco nell'est
on Ottobre 13, 2026 at 7:07 pm
"La città è interessata da una minaccia aerea ostile"

SENTENZA

sentenza.eu