Tool Use
topic on 4 shows · 9 statements across 8 episodes
Latent Space 
No Priors 
the Official SaaStr Podcast 
Sourcery
9 statements about Tool Use, every show
McKinzie: Tool use noticeably changes test-time scaling for visual reasoning
“We've seen exactly that, like the test time scaling slopes for, without tool use and with tool use for visual reasoning specifically are very noticeably different.”
Siddharth: Solving multimodality, reasoning, tool use, and coding yields ASI
“Turing's the world's leading research accelerator, working with all of these frontier labs to advance them along I would say the four pillars of superintelligence which is multimodality, reasoning, tool use, and coding. If you solve these four things, you will…”
Lambert: SFT cannot teach emergent tool use; models must learn via RL environments
“It's very easy to get the model to do tools if you prompt it to, but it's very hard to get the like RL model to learn that the tool is useful. And that's why it's to go through these things where it's like 80 failed tool uses and it still gets it or like it st…”
McKinzie: Tools prevent reasoning models from degrading during test-time compute
“We've in the past for our reasoning models talked a lot about test time scaling, and I think for a lot of problems you know, without tools, test time scaling might occasionally work and, but at some point the model is just kind of ranting in its internal chain…”
Mitchell: AI offloads tasks lacking comparative advantage to external tools
“I think like part of this is you can just allocate compute a lot more efficiently because you can defer stuff that the model doesn't have comparative advantage to doing to a tool that is like really well suited to doing that thing.”
Schluntz: Computer use is primarily a low-friction way to implement tool use
“I think most broadly, not just for like new things that weren't possible before, but as a much lower friction way to implement tool use.”
Albrecht: Code execution expands agent capabilities far beyond hard-coded tool calling
“Instead of worrying about like weird hard coded agents using tools, Like let's just make them able to actually write code robustly and make that code work and be able to debug that code, know if that code is safe to run, like get really good at the like code w…”
Mann: Knowledge Extraction Is Low-Risk AI Compared to Tool Use
“Take a portfolio approach, try some less risky use cases, like where knowledge extraction or summarization might be involved. And maybe some more risky use cases like tool use, where it's using that company's tooling, function calling.”
Liang: Language models should use calculators instead of computing internally
“There are cases where you want to just map natural language into say people call it tool use. Like you ask some question that reverse calculation, you should just use a calculator rather than trying to sort of quote unquote do it in the transformers head.”