1,841 mentions · 834 chunks · 141 episodes
...ent calls, it required humans in the loop… which required bureaucracy. But now, LLMs can do some levels of judgment automatically, with no humans in the loop. So now you can solve discovered problems by distilling new AI automation. T...
...Shapiro's Trycycle. An excellent pattern to extract compounding leverage out of LLMs. Just autonomously plan, autonomously implement, and then repeat!
LLMs can't forget about the context in their conversation, they are always drawn to it. So saying "come up with five different ideas and develop each" wor...
LLMs are the enabler of the infinite possibility of software we've all been waiting for. We just need the right vessel to activate that potential.
LLMs are great at making a passable version of any shitty idea. You can do a lot of damage and wasted time if you never ground truth it with people. If yo...
LLMs are for code what the Hall-Héroult was for aluminum. Before the Hall-Héroult process was invented in 1886, aluminum was treated as precious. It was p...
LLMs are amplifiers. Like levers, that can be hugely valuable… but also hugely dangerous.
LLMs take away the puzzle part of programming. The puzzle part of programming is where you can relax. Like doing sudoku puzzles that produce useful things...
..., the things we intended to do but never got around to. At a certain point with LLMs, you just kind of run out of a backlog. Contains this zinger: "Showing off your portfolio of bespoke aClaude Code projects and looking at others' por...
...ion debt of product teams is going down as we can burn through the backlog with LLMs. Engineers were the bottleneck so PMs had time to plan and think. [bp] But not any more!
...that means the power accretes on their turf. A raw deal for users. But now with LLMs, software isn't precious.
LLMs can do fiddly slogs that are meticulous and require expertise. Vercel is all about lots of small fiddly details for a great developer experience. You...
...nlikely to me. But a bottom-up AGI, where every person can marshal the power of LLMs to create compounding tools for themselves, feels way more plausible to me. It would also be a runaway process that it's hard to reason about the mul...
LLMs are great at complicated problems, but terrible at complex problems. Humans are bad at both. But LLMs have patience, which is the main requirement fo...
...eces and layers and the outcome still feels like a miracle. Markets, evolution, LLMs, and life itself all have this characteristic.
I wonder if the whole focus on AGI is downstream of LLMs talking like humans. Like, the idea of a planetary scale omniscient personality is easy to imagine, and also terrifying. Chatbots make this kind of f...
... Coders see coding as an end unto itself. Before, they looked the same. But now LLMs reveal the difference. Builders love LLMs, and coders hate them.
Systems that assume LLMs will be nearly perfect won't work. LLMs will never be perfect. Resilient systems assume that they can be confused.
LLMs can be made to be default-converging. Every input to them, if scoped small enough, it will do what a reasonable person would with that information. S...
...b. The expected danger of them is the multiplication of "powerful" and "naive." LLMs with access to sensitive data are the most confusable deputies ever!