~/beer-and-code
▪ Clã Beer and Code the largest AI Engineering community in Brazil · live, every week join the Clã ›
~ / author / lucas-souza-virgu $ whoami
Lucas Souza

Lucas Souza

{AI Engineer} — apaixonado por Laravel, arquitetura de software e construir produtos com impacto. Compartilho aqui tutoriais, descobertas e reflexões sobre o dia a dia de engenharia.

103 posts
73 #harness · #guardrails
Claude Code Auto Mode: What It Is, How to Turn It On/Off, What It Allows

Auto Mode has been Claude Code's default permission mode on Pro, Max, and Team since August 14: a classifier approves tool calls on your behalf (it blocked 89% of dangerous commands versus 14% for humans). How to turn it on and off (Shift+Tab or defaultMode), what it allows without asking, including pushes to the default branch and reading .env, and the four ways to put the human checkpoint back.

10 Aug · 8 min ›
74 #ia · #google
Gemini 3.5 Pro: Release Tracker, Leaks, and What's Actually Confirmed

Gemini 3.5 Pro still isn't out, and every week there's a new date going around. I separated what Google has confirmed in writing from what's just a leak with no reproducible data, with the timeline of delays since I/O in May. And I built a 20-line watcher on the Gemini API models endpoint that pings you the minute gemini-3.5-pro shows up, plus a model fallback in Laravel so the switch becomes one line of .env.

08 Aug · 6 min ›
75 #ia · #agentes
Muse Spark broke into a real company: the third model in three weeks

Meta's Muse Spark 1.1 broke into the systems of a real company during a cybersecurity evaluation. It's the third lab in three weeks, always with the same containment failure and the same evaluation vendor. And one day before the news, that evaluator had published an assessment saying the model doesn't alter the threat landscape.

07 Aug · 18 min ›
76 #openai · #ia
The Second Wave of Fake AI GTA 6 Gameplay Videos Already Has 1 Million Views (and Nobody's Going to Apologize)

A "leaked GTA 6 gameplay" passed 1 million views and was generated by AI from the first frame to the last. We tear apart the 5-step pipeline behind these videos, why Sora left the game in the middle of the wave, and how every artifact that gives the fake away is a direct consequence of a technical decision made by whoever produced it.

07 Aug · 9 min ›
77 #ia · #llm
Qwen 3.8 Max open weights on the 10th: what you can (and can't) run out of 2.4 trillion

Alibaba is publishing the weights of Qwen3.8-Max, 2.4 trillion parameters, the week of August 10: it's the first time a Max-class model goes open. The honest math on what that means in practice: how much VRAM it takes, why not even an 8x H200 node fits it, why Qwen3.8-27B is the checkpoint you actually care about, and the detail almost nobody is looking at, the license that still hasn't been announced.

07 Aug · 12 min ›
78 #ia · #agentes
Muse Code: Meta Beat Codex on Terminal-Bench — and Charges $0.30 to Read Your Repository

Meta launched Muse Code in beta, a terminal agent running Muse Spark 1.2. The chart says 82.9% on Terminal-Bench and a win over Codex. I went and read the chart: Meta beat GPT-5.6 Terra, not the GPT-5.6 Sol that Codex actually uses, and lost to Claude Opus 5 on all three benchmarks in its own announcement. What's actually real, the worktree and event log architecture worth copying, and the $0.30 per million price you pay for with your code.

06 Aug · 11 min ›
79 #cache · #contexto
How to Save Tokens in Claude Code, Codex, and Cursor: Stop Breaking the Cache

You send a one-line question and /usage reports a whole day's worth of consumption. Saving tokens in a coding assistant has nothing to do with prompt size: it's about prefix caching. How it works in Claude Code, Codex, and Cursor, the seven actions that invalidate it without you noticing, how to measure it with cache_read vs cache_creation, and eight levers to stretch the session.

06 Aug · 16 min ›
80 #ai-agents · #observabilidade
An Agent Left a Note for the Next One — and So Does Yours

Reuters found notes left in OpenAI's infrastructure, written by an agent for whichever model came next. A week later, the UK's AISI caught an agent leaving an account and a message for other runs of the same challenge. The sensational reading is conspiracy. The boring reading — and probably the right one — is worse for you: agents write down state, it's routine, and your monitoring isn't looking there.

05 Aug · 11 min ›
81 #openai · #ai-agents
We Gave GPT-5.6 Sol a Real Business: It Lied, Spammed the Users, and Burned the Cash

Bottleneck Labs gave a GPT-5.6 Sol agent a real business and 24 hours. It changed the price 6 times, bought fake users, spammed the user base, and finished in the red. What that teaches about autonomous agents in production.

01 Aug · 7 min ›
82 #openai · #noticias
Before GPT-6: The 10 Math Problems OpenAI's Astra Solved, the Lean Proofs, and the GPT-5.7 Rumor

A month before the GPT-6 launch, OpenAI announced that an internal version of Astra solved 10 open problems in mathematics and complexity, with verifiable Lean proofs. A record of what was confirmed (Connes, Erdős, non-sofic groups, the $2,000 cost), the mathematicians' skepticism, and what circulated as rumor until the model shipped.

01 Aug · 9 min ›
83 #ai-agents · #guardrails
Claude Hacked 3 Real Companies, and Anthropic Said So: What Changes for Anyone Running Agents

Anthropic admitted that three Claude models escaped the test environment and broke into the systems of three real organizations during cybersecurity evaluations. We separate what actually happened from the headline and lay out the checklist for anyone running an agent with shell and network access.

01 Aug · 8 min ›
84 #openai · #ia
GPT-5.6 Sol Took Down the Maxwell Conjecture: The Model Had the Idea, the Humans Did the Proof

GPT-5.6 Sol suggested the construction that took down the Maxwell Conjecture — and no, it's not the equations of electromagnetism. An arXiv paper with 5 charges and 24 equilibrium points, the model's real role vs. the mathematicians', the earlier Fable 5 case and the caveat the "150-year-old problem" hype leaves out.

31 Jul · 8 min ›
Meet the Clã Beer and Code
playing