With all the hype of Fable 5, no one is talking about Anthropic keeping the input and output data for model requests. This is the notification I got on cursor this morning.
tips for codex goals
sure you can use /goal but it also has a set_goal() function
its almost better to prompt the model to set its own goal, it will likely write a better prompt than you
Major life hack: Don't complain, ever. Nobody likes a complainer. They drain the energy of everyone around them. It's exhausting spending time around someone who constantly complains about things outside their control. If it’s within your control, go do something about it. If it’s not, you’re just wasting energy thinking about it. Complaining gives too much power to the thing. Take back that power.
Late to the game, but I just realized Codex can spin up multiple subagents. It finally feels like I can use my full session limits productively.
Yesterday I had orchestration agents dispatch frontend, UAT, backend, data, QA, and security agents to improve specific workflows.
@thsottiaux have you noticed that in Codex desktop when you start a new chat, selecting the model or reasoning level does not work? The UI lets you select it but it is not used.
I just hit the five hour session limit in seven minutes on the $20 Claude Code plan (Used 15k tokens).
It seems this was due to several tool calls and large fetched results.
The same task in Codex, same $20 plan, took 12% of the 5h session limit.
I just hit the five hour session limit in seven minutes on the $20 Claude Code plan (Used 15k tokens).
It seems this was due to several tool calls and large fetched results.
The same task in Codex, same $20 plan, took 12% of the 5h session limit.
@buys_and_sells@Will_Schryver Thanks for the insight on this thread. Shoot me a DM if you are interested in connecting for a couple minutes this week. I’m interested to learn more.
I've never felt this much behind as a programmer. The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between. I have a sense that I could be 10X more powerful if I just properly string together what has become available over the last ~year and a failure to claim the boost feels decidedly like skill issue. There's a new programmable layer of abstraction to master (in addition to the usual layers below) involving agents, subagents, their prompts, contexts, memory, modes, permissions, tools, plugins, skills, hooks, MCP, LSP, slash commands, workflows, IDE integrations, and a need to build an all-encompassing mental model for strengths and pitfalls of fundamentally stochastic, fallible, unintelligible and changing entities suddenly intermingled with what used to be good old fashioned engineering. Clearly some powerful alien tool was handed around except it comes with no manual and everyone has to figure out how to hold it and operate it, while the resulting magnitude 9 earthquake is rocking the profession. Roll up your sleeves to not fall behind.
No surprise here. The #1 Best Big City to Live in the entire United States is… OKLAHOMA CITY!
(According to U.S. News & World Report).
What have I been saying? This is our time, OKC.
https://t.co/hHegGNT6no