Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Nicola Alessi
Claude Opus 4.7: What the release notes don't tell you about token costs
Opus 4.7 dropped today. The headline numbers are real — 87.6% SWE-bench, +13% on coding benchmarks, triple the vision resolution. Worth upgrading. But there are three changes in the release notes that compound quietly: 1. New tokenizer The same input now maps to 1.0–1.35x more tokens depending on content type. On a typical codebase query, that's not nothing. 2. xhigh effort mode Sits between high and max. Reasons longer per turn. More output tokens on every step. 3.
I tracked every token my AI coding agent consumed for a week. 70% was waste.
Last week Anthropic announced tighter usage limits for Claude during peak hours. My timeline exploded with developers asking why they're hitting limits after 2-3 prompts. I'm the developer behind vexp, a local context engine for AI coding agents. Before building it, I did something nobody seems to do: I actually measured what's happening under the hood. The experiment I tracked token consumption on FastAPI v0.115.0 — the real open-source framework, ~800 Python files. Not a toy project.
How I Cut My AI Coding Agent's Token Usage by 65% (Without Changing Models)
I've been using Claude Code on a 200-file TypeScript project. The model is great. The token bill was not. The problem wasn't the model — it was what I was feeding it. Every session, the agent would read 30-40 files trying to orient itself before doing any actual work. Same files, same discoveries, same wasted tokens. Every single time. After a lot of trial and error, I got my average input tokens per query from about 8,200 down to 2,100. Here's what worked, in order of impact.
Show me your AI side project
AI is exploding right now, and I’m sure many of you are tinkering with cool side projects—whether it’s LLM experiments, automation tools, or something wild and unexpected. Let’s share what we’re building! Drop a comment with: Name/Description of your project Tech stack you’re using Biggest challenge you faced (or still facing) Demo link (if public) I’ll start: Lumigo 🔹 What it is: A smart shopping search engine that find the best products without bias or sponsored results (RIP Google).
Passive Rewilding of Old‐Established Plantations Into Native Forests
1 Introduction In the last centuries, human impact on natural ecosystems has increased exponentially (Díaz et al. 2019). This escalation coincided with the expansion of plantation programs across Europe and, later, worldwide (Freer-Smith et al. 2019; Messier et al. 2022; Simões et al. 2024).
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Nicola
Contact Nicola, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack