Ian Lucas

[Ian Lucas @RealIanLucas]

@charliwtquirks @daniel_mac8 Just give Codex the URL to the chat. It will extract the content and do whatever you like with it. You can also use the in-app browser to keep it all inside of Codex if you prefer vs the Chrome extension.

Also, yes, Prompt Escobar is amazing, lol

[Ian Lucas @RealIanLucas]

@Steve_Yegge Just have it Red Team/Steelman the opposite of what you want and it will get what you're after. Reverse psychology FTW

[Ian Lucas @RealIanLucas]

@v1ctus17 @thsottiaux That's for real. I'm about to get a 2nd Pro account and it will sting that much more not to have access to this Enterprise feature. Then again, it should be moving to Pro before too long, I would imagine...

[Ian Lucas @RealIanLucas]

@rileybrown I hope so!

[Ian Lucas @RealIanLucas]

@JustinBleuel @ChatGPTapp will do!

[Ian Lucas @RealIanLucas]

@JustinBleuel @ChatGPTapp And in long sessions, the screen jumps up to the middle of the thread while new agent content is being outputted and I can't scroll down and stay at the bottom until it is done outputting (it keeps jumping up to a much earlier point in the conversation thread).

[Ian Lucas @RealIanLucas]

@JustinBleuel @ChatGPTapp Usually random progress status spinning the decouples from actual progress through a plan

[Ian Lucas @RealIanLucas]

@tszzl I have a dream of hiking the Rockies with a Starlink connection and just talking to Codex (and Claude Code) as I go and occasionally resting to look at the results.

Solving for the "go outside" conundrum...

[Ian Lucas @RealIanLucas]

@sama Just use both!

[Ian Lucas @RealIanLucas]

@emollick I respect your reclamation of the em dash

[Ian Lucas @RealIanLucas]

@elonmusk @DannyLimanseta @grok based on past LLM releases from major labs (including, but not limited to, xAI), what is the timeline after the pre-training phase before a model becomes publicly available? Please give an average and a reasonable time window estimate based on actual historical releases.

[Ian Lucas @RealIanLucas]

@niccruzpatane I need this in my life immediately.

[Ian Lucas @RealIanLucas]

@DeryaTR_ In the Web UI, it couldn't even generate a 1-page DOCX yesterday without hitting some sort of session limit (which seems not to have been my overall usage limit, fwiw)

[Ian Lucas @RealIanLucas]

@karpathy Maybe by this time next year? When this level of ability is coupled with handling all business admin, marketing, and banking, an entrepreneurial Cambrian explosion will happen.

[Ian Lucas @RealIanLucas]

@emollick Their priorities are all out of quack

[Ian Lucas @RealIanLucas]

@BredsguardDalen Honorable mention

https://t.co/xwvxPxzNgE

[Ian Lucas @RealIanLucas]

@BredsguardDalen That whole album was fire.

My nomination for weirdest is this inexplicable European gem...

https://t.co/yACT0XvYgG

[Ian Lucas @RealIanLucas]

@deredleritt3r @_NathanCalvin Not to be outdone, ChatGPT says Codex for Lawyers FTW: https://t.co/buiC3NLesj

[Ian Lucas @RealIanLucas]

Claude says you can roll your own:

https://t.co/O7OXA3oRKR

"'Claude Code for lawyers' does not require a new product. It requires a legal Skills pack — a curated set of SKILL.md files that encode the analytical frameworks, document conventions, research methodologies, and workflow patterns that transform a general-purpose agent into a legal specialist. The chassis already exists: Claude Code for terminal-native lawyers, Cowork for everyone else, with Skills, MCP, persistent memory, sub-agents, and scheduled tasks providing the building blocks."