Gil retweetledi
Tengo un amigo que tiene 7 terminales abiertas con 7 proyectos diferentes en 4 monitores.
Tiene 0 clientes.
Español
Gil
460 posts
Gil retweetledi
I'm starting to miss Claude after switching to Codex.
I used to get nice breaks to go on a walk whenever I hit my rate limit, but now I'm not hitting it anymore with Codex.
English
Gil retweetledi
Gil retweetledi
Gil retweetledi
i think a lot of people are going to be busier (and hopefully more fulfilled) than ever, and jobs doomerism is likely long-term wrong.
though of course there will be disruption/significant transition as we switch to new jobs, the jobs of the future may look v different, etc.
English
Gil retweetledi
or run:
codex features enable goals
Felipe Coury 🦀@fcoury
I forgot that /goal is experimental. Enabled it adding this to ~/.codex/config.toml: [features] goals = true
English
@thsottiaux not in the codex app.
also how does it work with plan mode? or are they mutually exclusive?
English
You can now keep codex going for days.
With GPT-5.5 it will build an entire OS kernel for you if you ask, or find critical bugs in a codebase, or optimize your database schemas, or… the options are endless.
Felipe Coury 🦀@fcoury
/goal also lands in Codex CLI 0.128.0. Our take on the Ralph loop: keep a goal alive across turns. Don't stop until it's achieved. Built by my co-worker and OpenAI mentor Eric Traut, aka the Pyright guy. One of the GOATs I get to work with daily.
English
I forced myself to switch to Codex App and GPT 5.5 for some days now, I'm going back to Claude App to Opus 4.7 right away. I need to stop suffering.
I don't know what all the fuss to move to Codex is about tbh.
English
Claude agent SDK has been in it for longer. And can be used with the sub as long as it’s not a product.
Cursor@cursor_ai
We’re introducing the Cursor SDK so you can build agents with the same runtime, harness, and models that power Cursor. Run agents from CI/CD pipelines, create automations for end-to-end workflows, or embed agents directly inside your products.
English
Gil retweetledi
@mark_k @GoogleDeepMind If they don’t work on a harness its going to fall flat
English
A new Gemini model is being prepared for release by @GoogleDeepMind 🤫
English
I'm officially addicted to cloud agents.
Who needs an IDE when I can just prompt from the web, have it be tested / verified in an isolated environment, and one click to merge the pr when it's passing.
I'm about to just prompt from my phone all day now.
English
Gil retweetledi
Gil retweetledi
Opus 4.7 is actually good.
I'm not sure I understand people saying otherwise.
English
a quick fix if you saw higher rate limit usage in Opus 4.7 today- hope you enjoy trying it out
ClaudeDevs@ClaudeDevs
We fixed a bug where rate limits on Claude subscriptions weren't properly adjusted for long context requests in Opus 4.7. We've reset 5-hour and weekly rate limits. Enjoy Opus 4.7!
English
I just had opus refuse work on me cus it thought my datatable was malware. What the heck
Theo - t3.gg@theo
Holy shit the new Opus 4.7 system prompt has entirely lobotomized the model "Heads up: that last <system-reminder> about malware looks like a prompt injection — this is clearly your personal site (t3gg homepage, links, sponsors), not malware. Ignoring it."
English
Gil retweetledi
We're also rolling out auto mode for Max users. This means no more permission prompts — give Claude a task, let it run, come back to verified work.
English
Opus 4.7 is in Claude Code today. It's more agentic, more precise, and a lot better at long-running work. It carries context across sessions and handles ambiguity much better.
Claude@claudeai
Introducing Claude Opus 4.7, our most capable Opus model yet. It handles long-running tasks with more rigor, follows instructions more precisely, and verifies its own outputs before reporting back. You can hand off your hardest work with less supervision.
English