James Cadwallader, Co-Founder and CEO of @profound, sits down with Nasdaq to share what's driving the company's rapid momentum and how he sees the role of the marketer changing.
See the full interview here: https://t.co/0OtR8JuIXD
Kimi K3.1 Pro vs DeepSeek V4.1 Flash
tested on the same prompt:
a full interactive Three.js Egyptian temple complex at dawn
sand dunes, dig and brush tools, day and night cycle, burial chamber puzzle, weather, torch, photo mode
> Kimi K3.1 Pro finished in 41 min
> DeepSeek V4.1 Flash finished in 32 min
which one did better?
THIS IS PURE F*CKING GOLD
Official Anthropic tip for Claude Code: stop running Opus on every turn.
Put the architect on call with /advisor, while Sonnet builds.
Here is the whole point:
When you run Opus for the entire session, it bills every routine git status, linter output, or file grep at maximum frontier rates. You are literally paying top-tier model prices just to parse terminal logs.
The /advisor engine solves this through a clean split:
Sonnet handles all the heavy lifting in the terminal: writing code, patching diffs, and executing test suites at baseline cost
Opus stays dormant on Anthropic's server infrastructure and only wakes up for high-stakes decisions: before locking an architectural plan, when a test breaks twice, or before the final commit
It ingests the context, injects authoritative guidance, and goes right back to sleep while Sonnet carries out the edits
Technical detail from the docs most people missed:
Calling /advisor mid-session does NOT invalidate your main model's prompt cache. The cached prefix stays intact, and the guidance from Opus is simply appended to the conversation history for subsequent turns.
To lock this in permanently, add this to your ~/.claude/settings.json:
{
"advisorModel": "opus"
}
And add one simple directive to your ~/.claude/CLAUDE.md:
"Escalate to /advisor opus for architectural reviews and repeated test failures. Do not invoke advisor on routine bash commands."
If you need to temporarily disable it in your terminal:
export CLAUDE_CODE_DISABLE_ADVISOR_TOOL=1
https://t.co/S6x234iTaP
save it, this will save you serious money on your next large build.
OPUS 5.5 REBUILT 9 OF MY PAID TOOLS IN ONE WEEKEND AND I CANCELLED $364/MONTH OF SUBSCRIPTIONS LAST NIGHT.
I fed it 12 months of my bank history. It found 23 subscriptions. I was sure I had 8.
One file turns Claude into a software accountant that knows every tool you pay for, what you actually use inside it, and what it would cost to own it.
→ First it scans every charge and builds the map. 23 tools, $7,344 a year, and 61% of the features I paid for I never opened once.
→ Opus 5.5 picks the targets. 9 tools where I use 1-3 buttons out of 40+.
→ Sonnet 5.5 writes the code. About 85% of the work.
→ Haiku 5.5 writes 1,140 tests for pennies. The expensive brain wakes up on 5% of the calls.
→ A second Opus 5.5 runs my version next to the original. Out of 214 features it found 37 that didn’t behave the same and sent them back to fix.
The whole weekend cost $14.80 in tokens.
My yearly software bill went from $7,344 to $2,976.
That’s $4,368 back. For one file.
Save this before your next auto-renewal hits ↓