xAI really cooked with this. You can create a Grok voice agent with a real phone number in the xai console in 2 mins. Found this while randomly exploring. Create a Customer support bot with MCPs, tools, web search. in Two minutes. Crazy. @elonmusk

I tried Hermes Bots side by side with Grok Bot, and the biggest difference is how seamless Grok feels. It just works. Hermes Bots still need debugging and constant hand-holding. That difference alone can determine whether people adopt a product or abandon it. It also helps explain why there’s been so much "whoa's" and word of mouth around Grok Bot.

How do you estimate software projects in the age of AI agents? I gave ChatGPT the prompt in the screenshot. It estimated 18 months and $2 million for the migration scenario I described. That prompt is basically describing Asana’s Enzyme migration. Asana had estimated the migration would take at least 5 years and roughly $6 million. Using Codex, they finished it in about 𝟐 𝐰𝐞𝐞𝐤𝐬 𝐟𝐨𝐫 𝐚𝐫𝐨𝐮𝐧𝐝 $𝟏𝟐,𝟎𝟎𝟎. Bun’s recent migration is another example of agents doing work that would normally take years much faster. Jarred Sumner estimated that porting Bun from Zig to Rust manually would take 3 experienced engineers about a year. Using Claude agents, they migrated 𝟓𝟑𝟓,𝟎𝟎𝟎+ 𝐥𝐢𝐧𝐞𝐬 𝐨𝐟 𝐙𝐢𝐠 𝐢𝐧 𝟏𝟏 𝐝𝐚𝐲𝐬, with roughly $165,000 in model usage. Not every project will be like this. Some have dependencies, integrations, and a lot of coordination that still take real time. But for work that’s well-defined, verifiable, and can be parallelized, agents can completely change the math. Maybe that’s the new variable in software estimation: how much of the work can be broken into independent, 𝐯𝐞𝐫𝐢𝐟𝐢𝐚𝐛𝐥𝐞 tasks and run in parallel by agents? A project that looks like years of engineering effort can look very different once you answer that.

I think Claude just gave me the perfect word for how Claude speaks: aphorisms. I asked Opus 5 to turn a course syllabus into slides, and the result was pretty bad. After some feedback, it basically self-diagnosed the problem better than I could have: It was writing aphorisms instead of actually teaching. It was writing to sound sharp

I tested Hermes Bot and Grok Bot on the exact same task: helping me manage a livestream chat. And I can see why people are raving about Grok Bot. The one-word answer is: seamless. It just works. Most people don't have unlimited time to debug issues, babysit agents, or constantly figure out why something broke. Grok Bot seems to have that magic sauce that removes a lot of that friction. It has that rare “it just works” feeling when you use it. Check out my live test here:

I won't be surprised if ends up being the tool authored by @steipete that outlives all other tools by him. codexbar is something i use everyday for agent cost/usage visibility