More a practice than a project, but I'm working on using voice as much as possible to interact with computers. This started with mapping the Tap Assistance on my phone to ChatGPT voice, then vibe coding better voice transcription for my computer, then shifting increasing amounts of work to Claude Remote control, etc.
This is less of a latency/efficiency thing and more about disconnecting the eyes from a screen and fingers from a keyboard. The upside is more walking, flow and creativity.
For the non-coders here, you can query and analyze all of play.clickhouse.com in Sourcetable's chat interface. You can also ask it for the code produced so you can copy/paste that back into the Clickhouse interface.
I second this. Spreadsheets are the primary tool used for 15% of the U.S. economy. Productivity improvements will affect hundreds of millions of users globally. Each increment in progress is a massive time save and value add.
The criticisms broadly fall between "spreadsheets are bad" and "AI will cause more trouble than it solves".
This release is a dot in a trend towards everyone having a Goldman-Sachs level analyst at their disposal 24/7. This is a huge deal for the average person or business. Our expectation (disclaimer: I work in this space) is that spreadsheet intelligence will soon be a solved problem. The "harder" problem is the instruction set and human <> machine prompting.
For the "spreadsheets are bad" crowd -- sure, they have problems, but users have spoken and they are the preferred interface for analysis, project management and lightweight database work globally. All solutions to "the spreadsheet problem" come with their own UX and usability tradeoffs, so it'a a balance.
Congrats to the Claude team and looking forward to the next release!
For now we're pretty obsessed with the spreadsheet interface, but we do think of Sourcetable as a spreadsheet-based application platform, so there multi-modal plans in the future.
For now, one fun experience is loading the app on Mobile and just talking to your database. It's the same as talking from a desktop but can feel far more natural and the form factor let's you get quick business answers on the go.
Separate to the Superagents launch here, LLMs are excellent for keyword optimizations since the compression/summary/synthesis essentially comes for free out of the box. This isn't unique to Sourcetable, but I do find it extremely pleasant that vector analysis with LLMs is easy, not hard. SEM/SEO is all just math at the end of the day.
The main things we bring to the table are that the AI can write code and handle much larger datasets than fit in ChatGPT, etc., and also that Superagents you can pipe your data in without code or SaaS interface kludge, so you can ask much more complicated questions than you usually might if you're not great at cleaning, filtering or analyzing data.
As naive as this may sound, when I first moved to America and was deciding where to base myself, I first had to learn that there was a difference between Silicon Valley (i.e. Peninsula / South Bay) and San Francisco.
From there, San Francisco looks quite small, but many neighborhoods are worlds away from the action - Outer Richmond is not the density of networks you are looking for, for example (better than rest of world, suboptimal for SF).
Co-locating close to the center of these dense founder networks is the best way maximize luck and opportunity.
This map isn't perfect, but it makes it pretty obvious where you should move if you're interested in startups.
Career wise, moving to "the center of the network" is still the best decision I ever made.
Sourcetable.com | Product Marketing (contract) | San Francisco
We're building a spreadsheet-based operating system for the web, although on first touch Sourcetable feels more like Excel Copilot or "Cursor for spreadsheets".
We're looking for one Product Marketer to join our team in a part-time contract capacity in the Bay Area (San Francisco preferred). The requirement are that you need to be great at video storytelling and also be strong at spreadsheets & analysis.
Everyone on our team codes, and you should too. There's no technical requirement for the role, per-se, but we have found it is better this way.
This is completely excessive, but we threw our AI at solving fantasy sports analysis and added a bunch of native integrations and python libraries. It's pretty decent, and fun to just chat with the data.
Big props to Joseph Wilson (@pseudo-r) who maintains the unofficial ESPN API. https://github.com/pseudo-r/Public-ESPN-API. Reliably the best service for interacting with fantasy sports data and AI.
This was an interesting project to work on, mainly because the quality and popularity of API docs for various services really does impact the experience of untrained LLMs using them out of the box. It was fun to experience this outside of our regular B2B context, and my big takeaway from this project was just how much people are underestimating the importance of this as we experience the rise of the agentic web over the next 3 years. (Agents are users too!)
We included some easter egg cricket features, but we haven't found a free service the AI likes enough to bundle that in officially yet, so that'll come at a later date. (We're Aussies, so of course the fantasy Cricket analysis will improve over time : )
Perhaps you shouldn't care, although I find this to be a short-sighted perspective.
Agents are users now, and agent-friendly docs and libraries will be standard practice for the tools that want to thrive through broader industry adoption.
Similarly, perhaps you wouldn't care if your website wasn't easily parsable by crawlers, but if you'd like your work to appear in search results you might like to include a sitemap or structure the HTML a little.
Check out Sourcetable, you might like it for your AI spreadsheet work. It's much better than Excel copilot in every aspect (financial modeling, data science, data cleaning, agent tools, etc.)
Most people use it for analysis and ops work, + data science.
I find myself using Sourcetable to run our company: query the DB, analyze the user data, make projections, write copy, help with technical SEO (search the web, scrape data, check status codes, clean my sitemap, run vector space analysis etc.), talk to apps, financial modeling for our operating model + forecasting, etc.
The main idea I'm thinking about is LLM related: we're all having a social experience with machines (!) while building the machines (!!). I'm not sure my brain fully grasps that it's talking to silicon while I work.