Forums
Hey y'all, name's kazi
Love playing video games; love vibe coding. I'm a founder of IAIBPO, INC., a company focused on providing AI and Contact Center solutions. I'm currently building two apps unrelated to Call Centers, but focused on problems I've been having while working in this industry. One of them is STRING EX. Been building STRING EX for the past year. It lets anyone turn raw data into beautiful charts in seconds. No Excel formulas, no Power BI licensing, no learning curve. Just paste your data, pick your chart, then done. The web version's currently available at stringex.app and the mobile app is almost ready for the App Store. I run three companies simultaneously, have a wife and kid, and I build at 3am after everyone's asleep. STRING EX is owned under IAIBPO, INC., a company my dad, a longtime family friend, and I run together. I'm keeping it in the family.
If you wanna learn more about STRING EX, let's chat!!
Anyone else running Opus 4.7 yet? This one feels different (with CC harness)
Anthropic just shipped Opus 4.7 today and i had to write about it somewhere because the jump is weird.
I ran the same backlog task on 4.6 and 4.7 back to back. same repo, same prompt, same tools. 4.6 looped on a bug for 25 minutes and was not going to solve it. 4.7 closed it in eleven, and the part that freaked me out is that it paused in the middle to sanity-check an assumption i had not asked it to check. literally wrote "before i write this migration, let me verify the actual shape of the response object, because my assumption here might be wrong" and then went and verified it. unprompted.
That self-verification behavior is the thing. Vercel is reporting it does proofs on systems code before starting work. Hex says it flags missing data instead of making up plausible-but-wrong fallbacks. Genspark measured loop rates on hard queries and 4.7 basically stopped looping. different teams, different harnesses, same pattern.
the numbers are nuts too:
