Skip to content

Project

Vertex AI

Google Cloud's managed platform for building, training, and deploying machine learning models, including access to Gemini and other foundation models.

Current stories

buildOne report1 publisher

Spotify's Ads AI ties each production agent to one package and one owning team

Spotify's Ads AI multi-agent platform has produced about 20,000 ad creatives for more than 7,000 advertisers, senior engineer Pratik Rasam said. Each agent is its own Bazel package naming the team that reviews its changes and answers its alerts, and other teams can copy that part most easily.

Publishers:infoq.com

Reality

Evidence45
Adoption55
Hype gap+20
Incentives65
Confidence55
productOne report1 publisher

Teams leaving Nano Banana 2 by October 29 find Google's docs disagree on the 4K price

Google shuts off Nano Banana 2 on the Gemini API on October 29; its replacement, Nano Banana 2.1, lists at about half the price per image. Teams budgeting 4K should plan on the higher of two token counts in Google's own docs until an invoice settles it.

Publishers:reapi.ai

Reality

Evidence50
Adoption
Not scored
Hype gap+5
Incentives70
Confidence45
buildOne report1 publisher

One GCP VM runs an ML team's Airflow for under $150 a month against Composer's $350 estimate

One ML team moved Airflow off on-prem boxes onto a single GCP VM estimated at under $150 a month, against about $350 for Cloud Composer 3. Its published repo gives other teams a working build to price against their own Composer quote.

Publishers:dev.to

Reality

Evidence35
Adoption10
Hype gap+15
Incentives
Not scored
Confidence40
buildOne report1 publisher

Gemini's agentic video mode fails silently on Vertex AI when any of four settings is missing

Gemini's agentic video mode, pitched by Google as cutting long-video tokens 88%, still answers normally when misconfigured on Vertex AI, a developer found. The bill is the only symptom, so the author tests every setting in the outgoing request.

Publishers:dev.to

Reality

Evidence40
Adoption
Not scored
Hype gap+30
Incentives
Not scored
Confidence40
buildOne report1 publisher

A unique key written before the queue ack stops LLM retries from reordering moderation review

LLM moderation queues need at most one current classification per accepted report, stored under a unique key before the queue ack, a dev.to guide argues. It plans for timeouts, lost leases and racing workers, and keeps unclassified reports visibly pending so a replay can still find them.

Publishers:dev.to

Reality

Evidence30
Adoption
Not scored
Hype gap+5
Incentives40
Confidence35
buildOne report1 publisher

Circuit breaker state gets its own Redis database so a cache flush cannot reset it

Wiring the breaker_machines gem into a Rails app took an afternoon. Making a circuit actually open took a week. The decisions that survive are about which Redis database holds state and which integration sets its own threshold.

Publishers:dev.to

Reality

Evidence58
Adoption18
Hype gap+12
Incentives38
Confidence48
buildOne report1 publisher

The National Archives catalog API answers a rate limit with 200 OK and a 5,454-byte HTML shell

The catalog serves its single-page app shell for malformed requests and for throttling alike, so the status line tells you nothing. The only gate that holds under load is checking the content type before you parse.

Publishers:dev.to

Reality

Evidence52
Adoption10
Hype gap−12
Incentives25
Confidence58
buildOne report1 publisher

A hackathon agent refuses to tick a form item until the question is actually answered

Shipping meeting assistants mark coverage the moment a topic comes up. Junwei Lai's intake adjudicates each open item in its own call and defaults to insufficient, which pushes the missing answer back into the room while the patient is still there.

Publishers:dev.to

Reality

Evidence42
Adoption6
Hype gap+14
Incentives55
Confidence52
buildOne report1 publisher

Gemini 3.7 Flash goes GA on one model layer, and that is the actual news

Google put the same 3.7 Flash behind its API, Vertex, Gemini Enterprise and AI Mode in Search on August 13. The payoff is fewer evaluations to run, not a new capability tier.

Publishers:dev.to

Reality

Evidence42
Adoption38
Hype gap+14
Incentives68
Confidence36