If you added a few more tools that let the LLM modify code files that would directly serve requests, that would significantly speed up future responses and also ensure consistency. Code would act like memory. A direct HTTP request to the LLM is like a cache miss. You could still have the feedback mechanism allowing a bypass that causes an update to the code. Perhaps code just becomes a store of consistency for LLMs over time.
This was an unserious experiment meant to illustrate the gap and bottlenecks that are still there. I agree that there's a lot that could be done to optimize this kind of approach. But even if you did, I'm not sure the results would be viable and I'm pretty sure classic coding (with LLM assistance and all) would still outperform such a product.
You need to do more unserious experments. This one is perhaps the best stupid idea ive seen.
Maybe the browser should learn to talk back.
You could store the pages in the database and periodically generate a new version based on the current set of pages and the share of traffic they enjoy. You would get something that evolves and stabilizes in some niche. Have an innitial prompt like; "dinosaurs!" Then sit back and see the magic unfold.
On a long enough timeline, having anything stored in local hardware is going to be suspicious. Not surprised to see government embrace of crypto lead to increased scrutiny.
Perhaps integrating new information into models will at some point be so efficient that models offered by online services will always know about all new APIs, about every small library, and about every license change. That would give such models a significant advantage over local models, even if at some point good local models would become runnable by anyone.
Totally agree. By the same logic, we shouldn't release a billionaire murderer just because they can afford it. Being rich doesn't always correlate with risk.
Cash bail is an anachronism that makes a bunch of money at the expense of society's undesirables, so little progress is made on fixing it. See also the private prison system.
I've been using Codebuff (formerly manicode) for a few weeks. I think they have nailed the editing paradigm and I'm using it multiple times a day.
If you want to make a multi-file edit in cursor, you open composer, probably have to click to start a new composer session, type what you want, tell it which files it needs to include, watch it run through the change (seeing only an abbreviated version of the changes it makes), click apply all, then have to go and actually look at the real diff.
With codebuff, you open codebuff in terminal and just type what you want, and it will scan the whole directory to figure out which files to include. Then you can see the whole diff. It's way cleaner and faster for making large changes. Because it can run terminal commands, it's also really good at cleaning up after itself, e.g., removing files, renaming files, installing dependencies, etc.
Both tools need work in terms of reliability, but the workflow with Codebuff is 10x better.
