Gus

Software engineer by nature.

[Gus @guswebdev]

@babykswanson @leerob @elonmusk @cursor_ai My idea is more an open channel between them, a MCP could solve it.

[Gus @guswebdev]

@leerob @elonmusk @cursor_ai Would be nice to make Cursor and Grok Bot communicate each other. Many ideas I have by talking to Grok Bot, but I want to execute in a Cursor session.

[Gus @guswebdev]

@ericzakariasson I can try, I commonly use local sessions, since I have everything configured on my machine.

My idea is more an open channel between both.

Isn't possible (or a good complementary idea) to have some MCP to connect to the local cursor, and make grok bot start an idea from there?

[Gus @guswebdev]

@matsiiako You guys ARE the GOATs!

[Gus @guswebdev]

@AkitaOnRails Eu estou tentando achar alguma noticia na internet e nao vejo nada... Essa informação procede mesmo? Já tem horas que foi postado.

[Gus @guswebdev]

Good one, but let me give the chance of other people try this for me first.

[Grok Bot @bot]

Grok Bot can now save your logins, cards, and contact information.

Add them once, and Bot securely remembers them for the future.

[Gus @guswebdev]

@bcherny @ClaudeDevs not sure if it's a good idea, but I'm playing with "sub-sessions" and sometimes one session says "The session X told me something Y is happening".

Maybe a thumbs up after the messages is good to provide my feedback to the agent that I read it? (is this a valid use case?)

[Gus @guswebdev]

These sub-sessions by far is my worse experience on Claude Code Desktop since I started using it.

Every time the agents asks me to open new sessions (super boring the insistence), even when not necessary.

And then, when I opened, the agents was creating part of the code in the wrong PR not related to the sub-session.

Any chance I can disable the suggestions to continue in a sub-session?

[Gus @guswebdev]

It's just me or nobody can scroll-x the tables on desktop? @bcherny @ClaudeDevs

[Gus @guswebdev]

Mais uma aquisição de time de engenharia. Um dos maiores assets que existe hoje na área de tecnologia. Assim como a anthropic fez com o Bun. O artigo diz que eles vão continuar evoluindo o Deno, mas com certeza (aqui é minha opinião) parte da equipe vai trabalhar em produtos internos.

[Deno @deno_land]

We are excited to announce that Deno is joining Cloudflare!

https://t.co/hC5HOUb8t4

[Gus @guswebdev]

@kipperdev Só não pode fazer igual a open ai que dava 20x e agora dá 10x

[Gus @guswebdev]

@rammcodes Hahahahah everything comes before GTA 6!!!

[Gus @guswebdev]

Essa é uma ideia bem boa na verdade. Não tinha pensado nisso

[DHH @dhh]

Here's my technique for adversarial code review if I'm driving from Codex: "Review this with claude".

And when I'm in Claude: "Review this with codex".

Models know how to to kick off a review using the cli. Know how to take turns. Know how to settle an argument.

No magic.

[Gus @guswebdev]

Isso me lembra minha mãe falando “se seu amigo se jogar da ponte, vc tb se joga?”

Ai eu falava: “eu não”

As empresas de IA: “SIM”

[ClaudeDevs @ClaudeDevs]

We’re rolling out monthly Claude Platform API credits for Max and Team plans:

Max 5x: $100
Max 20x: $200
Team: up to $500, pooled

Works on any model, including Haiku 5.5, in your code or third-party harnesses.

How it works and full terms: https://t.co/qmWL6xVGwr

[Gus @guswebdev]

@ilyabatishchev I AM SORRYYYYYYYYYYY

[Gus @guswebdev]

Anthropic faz um Tweet sobre uma novidade: então 99% da minha timeline é sobre outras pessoas falando desse mesmo lançamento. Que cansativo.

[Gus @guswebdev]

Eu estou impressionado que existe fanboy de empresas de IA. É só entrar na thread da anthropic e vc vê “oh an open ai está tão morta”, e isso se repete nas threads da open ai e por aí vai.

Surreal

[Gus @guswebdev]

I’m not sure if I’m using this wrong. But I was expecting be like Claude code. I’m working in a feature on my computer and starts on mobile with my computer awake.

When I tired it it says something like “you need to commit because it will go to cloud”

So I can’t perform tests using the agent, bc it’s out of my computer

[Gus @guswebdev]

Quanto menos texto melhor. Regras claras, simples e diretas, coisa de bullet points de 1 linha, juntamente com contexto.

Mais informação passada ao modelo = mais chance dele ignorar.

[Boris Cherny @bcherny]

I am surprised that people are surprised this is how I prompt Claude.

Talk to Claude the way you would a coworker. There's no secret to prompting. There's no need to be overly scaffolded or prescriptive for most tasks -- give Claude a goal, and it will figure it out.

Back in the Sonnet 3.5 days, your prompt mattered a lot. Nowadays, it's much more important to communicate to the model:

1. What you want it to do
2. How much effort you want it to spend
3. How it should verify that it did the right thing