[BLOG] The Power BI modeling MCP server in plain English
sqlgene.com/2025/11/19/the-p…
Replying to @simonw @nateberkopec
It feels like auto mode and having a separate decision model solves a lot of problems not handled by a single-model approach.
Replying to @1ovthafew
Don't jynx things
oracle.com/security-alerts/a…
Replying to @meetshukla_
What Higgsfield is doing, as a business, should be illegal. Nothing good can come of this in general.
Replying to @karishnu
How could they possibly benefit from weak keys they already control? I may be missing obvious but I don't get it
Replying to @anthonyronning
They might also just eat the cost on some and not cache it
Replying to @kunchenguid
Because they don't ship their org chart like OpenAI does 😛
People are trusting personal agents to move money between accounts? 👀😬
Duet's hardest job is deciding when to interrupt you, (like all proactive agents) and Anthropic says it's still tuning that.
Its own FAQ warns it can misread a thread, misjudge what's urgent, or miss something that lands between check-ins.
Before you join the waitlist: the background check-ins count against your Pro or Max limits. It asks before it sends, pays, signs or deletes, and some actions stay off-limits even with your approval, like moving money between accounts.
Replying to @TheAmolAvasare
Are you all going to finally have good support for MS Teams instead of just Slack? 😜





