71–80 of 460 posts
I don't always write correct code, either. My code sure as hell is plausible but it might still contain subtle bugs every now and then.
In other words: 100% correctness was never the bar LLMs need to pass. They just need to come close enough.
LLMs have no idea what "correct" means. Anything they happen to get "correct" is the result of probability applied to their large training database. Being wrong will always be not only possible but also likely any time you ask for something that is not well represented in it's training data. The user has no way to know if this is the case so they are basically flying blind and hoping for the best. Relying on an LLM f…
This is about to change very soon. Unlike many other domains (such as greenfield scientific discovery), most coding problems for which we can write tests and benchmarks are "verifiable domains". This means an LLM can autogenerated millions of code problem prompts, attempt millions of solutions (both working and non-working), and from the working solutions, penalize answers that have poor performance. The resulting sy…
If Im the govt, Id be foaming at the mouth - those projects that used to require enormous funding now will supposedly require much less.
Hmmm, what to do? Oh I know. Lets invest in Digital ID-like projects. Fun.
Earlier quoted context omitted.
That's actually a great question. Truth be told the best way right now is to grab Codex CLI or Claude CLI (I strongly prefer Codex, but Claude has its fans), and just start. Immediately. Then go hard for a few months and you'll develop the skills you need. A few tips for a quickstart: Give yourself permission to play. Understand basic concepts like context window, compaction, tokens, chain of thought and reasoning, a…
You're not really answering the question are you? Your answer is to play with it. Cool. But why cant you and others put together a proper guide lol? It cant be that hard. Go ahead and do it - it'll challenge the Anti-AI posters you are referencing. I and others want to see that debate.
Write a lambda that takes an S3 PUT event and inserts the rows of a comma separated file into a Postgres database.
Naive implementation: download the file from s3 and do a bulk insert - it would have taken 20 minutes and what Claude did at first.
I had to tell it to use the AWS sql extension to Postgres that will load a file directly from S3 into a table. It took 20 seconds.
I treat coding agents like junior developers.
Their default solution is to keep digging. It has a compounding effect of generating more and more code. If they implement something with a not-so-great approach, they'll keep adding workarounds or redundant code every time they run into limitations later. If you tell them the code is slow, they'll try to add optimized fast paths (more code), specialized routines (more code), custom data structures (even more code).…
Their default solution is to keep digging. It has a compounding effect of generating more and more code. If they implement something with a not-so-great approach, they'll keep adding workarounds or redundant code every time they run into limitations later. If you tell them the code is slow, they'll try to add optimized fast paths (more code), specialized routines (more code), custom data structures (even more code).…
You need to do this when coding manually as well, but the speed at which AI tools can output bad code means it's so much more important.
The difference for me recently Write a lambda that takes an S3 PUT event and inserts the rows of a comma separated file into a Postgres database. Naive implementation: download the file from s3 and do a bulk insert - it would have taken 20 minutes and what Claude did at first. I had to tell it to use the AWS sql extension to Postgres that will load a file directly from S3 into a table. It took 20 seconds. I treat cod…
Earlier quoted context omitted.
It’s easy to get AI to write bad code. Turns out you still need coding skills to get AI to write good code. But those who have figured it out can crank out working systems at a shocking pace.
I am sorry for asking, but... is there guide even on how to "figure it out"? Otherwise, how are you so sure about it?
This series of articles is gold.
Unsurprisingly, writing good software with AI follows the same principles as writing it without AI. Keep scopes small. Ship, refactor, optimize, and write tests as you go.
Most humans also write plausible code.
LLMs piggyback on human knowledge encoded in all the texts they were trained on without understanding what they're doing. Humans would execute that code and validate it. From plausible it'd becomes hey, it does this and this is what I want. LLMs skip that part, they really have no understanding other than the statistical patterns they infer from their training and they really don't need any for what they are.
What a shame your human reasoning and "true understanding" led you astray here.
Earlier quoted context omitted.
Supposedly the frontier LLMs are multimodal and trained on images as well, though I don't know how much that helps for tasks that don't use the native image input/output support. Whatever the cause, LLMs have gotten significantly better over time at generating SVGs of pelicans riding bicycles: https://simonwillison.net/tags/pelican-riding-a-bicycle/ But they're still not very good.
I have to admit I'm seeing this for the first time and am somewhat impressed by the results and even think they will get better with more training, why not... But are these multimodal LLMs still LLMs though? I mean, they're still LLMs but with a sidecar that does other things and the training of the image takes place outside the LLMs so in a way the LLMs still don't "know" anything about these images, they're just ge…