Posts

Warnings and ClaimReview?

\@nadaawg via Threads on Jul 6, 2023 But what about that feature where you tap the Search button twice and it pops open the keyboard? \@spotify way ahead of the curve Single-tap. Screenshot taken manu...

\@gergelyorosz What are good (and efficient) alternatives to ChatGPT \for writing code\ or coding-related topics? So not asking about Copilot alternatives. But GenAI "chat windows" that have been trai...

\@matifaure Thanks for the recommendation, it's actually great for searching! I wish I could ask it to narrow search results to a given time period though (cc \@perplexityai) On Twitter Jul 7, 2023 It...

This is an incomplete doc about browser site search shortcuts. You can modify your web browser so that after jumping to your address bar / 'omnibox' ( Cmd+L ) you can type a shortcut to search via a p...

https://blog.kagi.com/: Kagi is building a novel ad-free, paid search engine and a powerful web browser as a part of our mission to humanize the web. Kagi: Kagi's approach to AI in search Kagi Search...

This is an incomplete doc about search query length limits. From Perplexity AI's marketing email today: > Longer Input Limits > > Did you know Perplexity can write code, essays, and summarize articles...

This is an incomplete doc about search audits, or search engine audits. This is overly self-referential at this time. Search audits, as a form of "algorithm audit", are systematic approaches to evalua...

Inflection AI PI feedback interface This is in Google Forms. Screenshot taken with GoFullPage (distortions possible) at: 2023-07-01 08:18:06 Inflection AI PI sharing interface (via an example query-pr...

This tweet is a reply—from the same author—to the tweet in: very few worthwhile tasks? (weblink). [ highlighting added] \@benedictevans In other words, I think the text prompt is a poor UI , quite sep...

status: unread (2023-06-30 17:06:56) Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts bibtex @inproceedings{zamfirescu-pereira2023johnny, author = {Zamfirescu-Pereira,...

Learned how to use git status --short and create git aliases to filter out _site directory changes from Jekyll builds. Includes search tool comparisons using You.com, Perplexity AI, and Phind.

Responds to Benedict Evans' tweet about ChatGPT tasks, arguing the challenge isn't describing tasks briefly but finding the right prompts that connect searchers to their goals. Draws on dissertation research about how data engineers grow queries from code and conversation seeds.

Downloaded. > You’re all set > > Once embeddings are finished being generated, you can specify Cody’s context and start asking questions in the Cody Chat. Current status: "Generating repositories embe...

Follow-up: very few 2-3 sentence descriptions connect (weblog). What is a "worthwhile task"? [ highlighting added] \@benedictevans The more I look at chatGPT, the more I think that the fact NLP didn’t...

the definition(s) and use(s) of "prompt engineering" will continue to evolve, shapeshift, fragment and become even more multiple and context-dependent. But still a useful handle? [ highlighting added]...

Comparative screenshot collection showing initial search results from seven generative search tools for the query about which SUV brand is best.

\@generativist via Twitter on Jun 26, 2023 i imagine there’s no alpha left in adding the word “open” to various names anymore, right? My first thought in response to this was that someone should write...

Follow-up: [\[I want to buy a new SUV which brand is best?\]](/2023/06/28/i-want-to-buy-a-new-suv-which-brand-is-best). I don't think ads[1] are necessarily wrong to have in search results (despite th...

Flagging two excerpts from a recent Google Research blogpost