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!
> Each increment in progress is a massive time save and value add.
Based on the history of digitalization of businesses from the 1980s onwards, the spreadsheets will just balloon in number and size and there will be more rules and more procedures and more forms and reports to file until the efficiency gains are neutralized (or almost neutralized).
[founder here] Zapier, n8n, Agentkit, etc all have the user define a flowchart in software. This is a lot of work to set up and brittle -- can't work around edge cases & nuance.
We use an agent for execution -- so the LLM decides what to do at every step. No flowchart at all -- just text instructions.
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.
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.
reply