~/beer-and-code
▪ Clã Beer and Code the largest AI Engineering community in Brazil · live, every week join the Clã ›
~ / news $ ls -la

News

Releases, news, and trends from the world of software development.

77 news
01 #openai · #cache
GPT-6.2 Astra vs Fable 5.2: same price per token, but which one is cheaper for your agent?

GPT-6.2 Astra launched at $8/$40, the exact price of Claude Fable 5.2, and tied it at 174 on the Epoch Capabilities Index. But cache reads cost twice as much and a surcharge kicks in above 272K tokens. The math for a real agent session, what is lab data and what is independent, and why there was never a 6.1 Astra.

18 Nov · 15 min ›
02 #google · #ai-agents
Claude Meetings: Claude joins your call and starts the work before it ends

Anthropic launched Claude Meetings in beta: Claude joins your Google Meet call, takes notes and builds docs and whiteboards live. How to turn it on, what gets stored, what it costs and the gotchas.

16 Nov · 10 min ›
03 #laravel · #google
Gemini 4 Hydrogen vs Opus 5.5: 2.7x Cheaper per Token, but Should You Swap It Into Your Agent?

Gemini 4 Hydrogen costs 2.7x less than Claude Opus 5.5 per token and has a free tier. But where your coding agent lives, Opus still holds. Benchmarks side by side (Google vs Anthropic), the math on a cached agentic session, which Gemini 4 to use after Carbon and Argon double in price on 12/1, and a Laravel fallback with the list of what breaks when you switch.

16 Nov · 10 min ›
04 #ai-agents · #harness
Dreaming: what Anthropic found about AI agent memory (and what it changes in your harness)

Anthropic measured what actually works in AI agent memory: four layers, telling the agent what memory is for instead of rules, and dreaming, an offline step where the agent rereads transcripts and fixes its own memory. CL-Bench, Pokémon and wiki vs search numbers, plus Dreams API code and how to apply it in Claude Code.

11 Nov · 15 min ›
05 #claude · #anthropic
Fable 5.2 vs Opus 5.5: twice the price per token, half the cost per task?

Claude Fable 5.2 launched today 20% cheaper than 5.1, but it still costs twice as much as Opus 5.5 per token. Official benchmarks against Opus 5.5, Fable 5.1 and GPT-6 Astra, the cost of an agentic session with caching, what Mythos 5.2 is, and a decision tree for when each model is worth it.

09 Nov · 13 min ›
06 #ia · #ai-agents
Claude Code stopped cloning games: what AI has already done with reverse engineering and why Anthropic hit the brakes now

Anthropic confirmed two sentences in Claude Code's prompt that stop it from recreating existing games. What AI has already done with game reverse engineering, the damage to the market, and why the brakes came now.

31 Oct · 19 min ›
07 #openai · #ai-agents
GPT-6.1 Terra vs Opus 5.5: a quarter of the price per token, but should you swap Claude out of your agent?

GPT-6.1 Terra costs a quarter of Opus 5.5 per token, and OpenAI says it comes out 9x cheaper per task. We ran the numbers per solved task, separated lab numbers from independent data, and show which agent the swap makes sense for (and which it doesn't).

31 Oct · 15 min ›
08 #claude · #anthropic
Claude Ultra: Max 20x lost the 5-hour limit, but the weekly cap stayed

Max 20x became Claude Ultra and lost the 5-hour limit, but only on verified accounts. The weekly cap is the same: 10x Pro. What changed, why "20x" vanished from the name, and how to use /usage to find out which limit is actually hitting you.

31 Oct · 10 min ›
09 #claude · #anthropic
Claude Code updates in October 2026: the 8 changes that hit your wallet and your workflow

The 22 Claude Code releases of October 2026 (2.1.287 to 2.1.310), filtered by what touches cost and workflow: Haiku 5.5 at $0.10/$0.50 per MTok, idle compaction before the 1-hour cache expires, a /usage that fixes things with one key, a 5-hour limit warning when resuming a conversation, fast mode out of preview, /auto-mode-setup, fork subagents on in claude -p, and the Monitor tool on Bedrock, Vertex and Foundry. With the version for each one and what to do about it.

30 Oct · 12 min ›
10 #google · #alucinacao
Gemini 4 Carbon: benchmarks, pricing and when developers get it

Google announced Gemini 4 Carbon two weeks after Argon, and it already leads the Artificial Analysis index. But there's no public API, no model ID and no date. What Google published, what third parties measured (where it loses to Claude), the hallucination rate that went from 4% to 11%, the price that doubles after the introductory period, and a watcher that tells you when the model lands in the Gemini API.

29 Oct · 9 min ›
11 #ai-agents · #harness
Minimalist harness: why new models need fewer rules, fewer tools and less prompt

The harness that saved your agent last year is the one getting in its way now. Every model generation turns the previous harness's crutches into noise: ALL-CAPS rules, redundant tools, giant few-shot blocks, rigid orchestration. What the official Anthropic and OpenAI guides tell you to remove, Rich Sutton's lesson applied to harnesses, and how to prove with evals that removing things didn't make anything worse.

29 Oct · 14 min ›
12 #ai-agents · #harness
Agent Skills is now an open standard: what changes for your SKILL.md

On Oct 22, 2026, Anthropic donated the Agent Skills standard to the Agentic AI Foundation, the same path MCP took. What agent skills are, how SKILL.md progressive loading works, an audit of the 8 skills that run this blog, and a checklist for the skills you already have.

28 Oct · 12 min ›
Meet the Clã Beer and Code
playing