A missed call is often a lost customer.
Our AI voice agents answer every call instantly, qualify leads, and schedule appointments while your team focuses on closing deals.
Launching soon.
Join the waitlist at https://t.co/iAHig5s2I1
I don't know why everyone forgot that Openai has a deal with the department of war for mass surveillance of people... openai is less trustworthy among anthropic and openai... Aside from these facts I will still move to codex from claude code just because 5.5sol > 4.8 opus
@ajambrosino@jxnlco Game dev is not about code, it's a perfect combination of operating game engine, 3D modeling, game asset, voice design and obvsly coding... Until we develop an environment where all these things catch up together, there won't be any production ready vibe coded game...
@sama He probably can't digest the fact that the company he left for Tesla, is building world's best model right now... Similar like when your ex becomes hotter...
@iuditg@ConnorTalksAI same question, every time you change the model from claude to codex, do you ask the agents to understand the codebase first with all the changes, or you just start working with the next prompt from where you left your work with last model?
A @ycombinator partner (very active on X) asked me for $250k with a guarantee acceptance to their next batch๐ญ
He said you'll raise few millions after batch anyways so 250k will be nothing.
What happened to yc๐ญ๐ญ
PSA: if you care about your data and infrastructure then please *donโt* run your coding agent in yolo mode
To secure your workspace I recommend the following:
1. Use โApprove for meโ - you can have codex review what itโll run with a sub agent to make sure that itโs not destructive!
2. Use Rules - you can set up a rule for codes to never run destructive commands like โrm - rfโ, this needs to be in a .rules file and you can ask codex to create it too
3. Setup a PreToolUse Hook - you can ask codex to set this up for you as well
If you're having issues with your usage limits, I really recommend turning down reasoning effort vs what you used in 5.5.
5.6 Sol Medium and 5.5 Medium are not 1:1, and 5.6 Sol Low is the default for a reason!
You probably don't need to use xhigh except for very tough problems.
We desperately need a smart model router.
1. Weโre seeing a model explosion: GPT-5.6, Grok 4.5, Muse Spark 1.1, GLM-5.2, and Fable 5 all launched within the past month.
2. Even for a single model family like GPT-5.6, there're 3 (Sol, Terra, Luna) and 5 reasoning-effort levels.
That is far too many decisions for users to make manually.
The best model should be selected automatically based on the task, latency, quality, and cost.