This could be on the board for the opening credits of the next Simpsons episode.

Since having problems with a favicon in search myself recently, I'm noticing it a lot more. Amazon UK is a new spot today (the www.)

I got stung by a wasp today and it was actually OK. No need to panic anymore.

Another BrightonSEO, and a different event to speak at! This time it was the Search & Social Advertising Show, speaking about 'How to measure the impact of LinkedIn Ads with zero clicks'. Here's the deck: speakerdeck.com/richlawre/how-…

Tech SEO Tips this week has tips on Article Schema, plus speaker decks & talks from Brighton SEO Sep 2023 including Richard Lawrence, Ruth 🐾, Katy Powell, Gus Pelogia, Aleyda Solis 🕊️ & much more. Subscribe for more: eepurl.com/hMUKuf #SEO #Newsletter #TechSEOTips #SubscribeNow.

Anyone else finding that the GPT-4 API is particularly awful in terms of output compared to the ChatGPT UI at the moment?

Sometimes, it’s hard to recall what you must search for to find what you remember. 🤪 We used the new Sanity Embeddings Index API to create a semantic search tool that suggests results based on meaning and document context, not just exact text matches.

We're rolling out new features and improvements that developers have been asking for: 1. Our new model GPT-4 Turbo supports 128K context and has fresher knowledge than GPT-4. Its input and output tokens are respectively 3× and 2× less expensive than GPT-4. It’s available now to

Check out this demo from Google Research of Gemini's reasoning capabilities to understand and reason about users' intent, use tools, and generate bespoke user experiences that go beyond chat interfaces ↓ #GeminiAI

After spending many hours trying to schedule a task with Celery Beat, I've sacked it off and have used Prefect. Anyone else resorting to Twitter search for help in the future should do too.

So in GA4, pagePath could have a trailing slash whilst landingPage may not. And this is why my things were borked. Excellent.

Already upgraded my side project to using GPT-4o via the API, but not seeing a major improvement in quality so far. It's a tool that conducts 2 levels of analysis on images...the 1st (higher) level seems to have no change. The 2nd (more detailed) level is perhaps a bit better.

GPT-4o now seems to be a bit better for supporting application development. It doesn't often replace random parts of a component with comments when you're trying to fix, plus it seems to better take into account the styling of any examples you give it when it helps create.

A couple of years ago I was tearing my hair out for hours and hours trying to get Docker to work. Today, I set up a webhook on Cloud Run in about 30mins. LLMs really have opened up so many doors.

We’re testing SearchGPT, a temporary prototype of new AI search features that give you fast and timely answers with clear and relevant sources. We’re launching with a small group of users for feedback and plan to integrate the experience into ChatGPT. openai.com/index/searchgp…

Don't really get the hype around Claude Sonnet 3.5. It hasn't managed to help me with anything that GPT-4o hasn't been able to help me with. It's also been incorrect in each case so far.

Well this is a bit annoying

How did LinkedIn grow to the size it is when it's held together by tape? Trying to refresh access_token, says I can't because the state parameter was modified. Solution is maybe to log out & in. Try to login & asks for a code to be sent to my phone which never arrive. The end.