Mike Noe
mikenoe@mastodon.social
<p>ML/AI Engineer & Technical Leader | Production ML Systems | Real-Time Bidding & AdTech</p>
Posts
-
View post
@overcastfm@mastodon.social “Promos & Reruns filter” This is awesome! I've always hated this, "dump all your garbage on my holiday weekend” crap. It never occurred to me that Overcast could actually detect and block them. Thank you, thank you!
-
View post
RE: https://hachyderm.io/@estherschindler/116382916321976268 So it was engagement, not the child porn or racism. OK
-
View post
I added prompt caching to my Anthropic Batch API workflow. The hit rate was 0%. Each model has a minimum cacheable token count — 4,096 for Haiku 4.5. If your cache_control block is below that, the API silently ignores it. Successful response, zero cache reads, no warning. My IAB taxonomy prompt was 1,064 tokens. Well under the threshold. Full write-up: https://mikenoe.com/posts/prompt-caching-classivore/ #AnthropicAPI #LLM #PromptCaching #AIEngineering
-
View post
1/2 After years as a CTO, I&#39;m building something of my own. A few months in, the &quot;something&quot; is Classivore — an API that does IAB content classification, brand-safety scoring, and sentiment behind one consistent shape. Predictable per-request pricing, open-source training pipeline on GitHub. If you&#39;ve ever tried to bolt off-the-shelf classification onto an ad-tech stack, you know how rare both of those are. #AdTech #AI #Consulting
-
View post
37% → 78%. Doubled my web scraper&#39;s success rate by swapping requests for curl_cffi to mimic Chrome&#39;s TLS handshake. Bonus: deleting 22 lines of &quot;defensive&quot; header overrides added another 2pp. They were undermining the impersonation. Modern WAFs fingerprint TLS ClientHello and HTTP/2 SETTINGS, not User-Agents. https://mikenoe.com/posts/tls-fingerprinting-curl-cffi/ #python #webscraping #ai
-
View post
@caseyliss how did you learn that your park bench had MMW coverage? Does the phone show an indicator, did you see it on a map, or luck?