461–470 of 819 posts
Earlier quoted context omitted.
His "pelican riding a bicycle" tests are now a classic and AI shops are benchmaxxing for it
If they were testing that it'd work more often. Other things you can ask that they're still clearly not optimizing for are ASCII art and directions between different locations. Complete fabrications 100% of the time.
Anecdotal evidence. I have a fairly large web application with ~200k LoC. Gave the same prompt to Sonnet 4.5 (Claude Code) and GPT-5-Codex (Codex CLI). "implement a fuzzy search for conversations and reports either when selecting "Go to Conversation" or "Go to Report" and typing the title or when the user types in the title in the main input field, and none of the standard elements match, a search starts with a 2s de…
I'm not trying to be offensive here, feel the need to indicate that. But that prompt leads me to believe that you're going to get rather 'random' results due to leaving SO much room for interpretation. Also, in my experience, punctuation is important - particularly for pacing and grouping of logical 'parts' of a task and your prompt reads like a run on sentence. Making a lot of assumptions here - but I bet if I were…
Earlier quoted context omitted.
I am almost convinced your comment is parody but I am not entirely sure. You want proof for critical/supportive criticism? Then almost in the same sentence you make an insane claim without backing this up by any evidence.
Well, here's an even more insane claim: I'm infinity times more productive, as I just wouldn't even start projects without the LLM to sidestep my ADHD. Then, when the LLM invariably fucks up, I step in and finish things myself! Here are a few projects that I made these past few months that wouldn't have been possible without LLMs: * https://github.com/skorokithakis/dracula - A simple blood test viewer. * https://www.…
hn has no markdown support at all right now. It's just this https://news.ycombinator.com/formatdoc
Earlier quoted context omitted.
I'm not trying to be offensive here, feel the need to indicate that. But that prompt leads me to believe that you're going to get rather 'random' results due to leaving SO much room for interpretation. Also, in my experience, punctuation is important - particularly for pacing and grouping of logical 'parts' of a task and your prompt reads like a run on sentence. Making a lot of assumptions here - but I bet if I were…
I think that is an interesting observation and I generally agree. Your point about prompting quality is very valid and for larger features I always use PRDs that are 5-20x the prompt. The thing is my "experiment" is one that represents a fairly common use case: this feature is actually pretty small and embeds into an pre-existing UI structure - in a larger codebase. GPT-5-Codex allows me to write a pretty quick & dir…
But you are right that codex does that all by default. I just get frustrated when I ask it something simple and it spends half an hour researching code first.
To @simonw and all the coding agent and LLM benchmarkers out there: please, always publish the elapsed time for the task to complete successfully! I know this was just a "it works straight in claude.ai" post, but still, nowhere in the transcript there's a timestamp of any kind. Durations seem to be COMPLETELY missing from the LLM coding leaderboards everywhere [1] [2] [3] There's a huge difference in time-to-completi…
That's a good call, I'll try to remember that for next time.
Earlier quoted context omitted.
I think that is an interesting observation and I generally agree. Your point about prompting quality is very valid and for larger features I always use PRDs that are 5-20x the prompt. The thing is my "experiment" is one that represents a fairly common use case: this feature is actually pretty small and embeds into an pre-existing UI structure - in a larger codebase. GPT-5-Codex allows me to write a pretty quick & dir…
I tend to tell claude to research what is already there, and think hard, and that gives me much better per-prompt results. But you are right that codex does that all by default. I just get frustrated when I ask it something simple and it spends half an hour researching code first.
Earlier quoted context omitted.
I'm not trying to be offensive here, feel the need to indicate that. But that prompt leads me to believe that you're going to get rather 'random' results due to leaving SO much room for interpretation. Also, in my experience, punctuation is important - particularly for pacing and grouping of logical 'parts' of a task and your prompt reads like a run on sentence. Making a lot of assumptions here - but I bet if I were…
> I bet if I were in your shoes and looking to write a prompt to start a task of a similar type that my prompt would have been 5 to 20x the length of yours Why would you need such extensive prompting just to get the model to not re-implement authentication logic, for example? It already has access to all of the existing code, shouldn't it just take advantage of what's already there? A 20x longer prompt doesn't sound…
It's not a good idea to have any coding agent put unnecessary amounts of lines into the context window in order to understand your code base.
Performance of all llms drop drastically when the context window is filled or full. The purpose of being more specific with your prompts is that you spend a little bit more tokens up front to make the task a lot more efficient and more likely to result in success.
At least that's how it is today. We're probably a breakthrough or two away from the type of vibe coding experience non-coders want. Or it may never happen, and the developers who have coding knowledge will be the only ones to fully utilize coding agents and it will only become more powerful over time.
Earlier quoted context omitted.
Well, here's an even more insane claim: I'm infinity times more productive, as I just wouldn't even start projects without the LLM to sidestep my ADHD. Then, when the LLM invariably fucks up, I step in and finish things myself! Here are a few projects that I made these past few months that wouldn't have been possible without LLMs: * https://github.com/skorokithakis/dracula - A simple blood test viewer. * https://www.…
> EDIT hn has no markdown support at all right now. It's just this https://news.ycombinator.com/formatdoc