It's early days and we don't fully understand LLM behavior to the extent that we can assume questions like this about agent design are resolved. For instance, is an agent smarter with Claude Code's tools or `exec_command` like Codex? And does that remain true for each subsequent model release?
I love sitting in those planning meetings, too. /s
This is exactly right. We've adapted our workflow to kick off a task and then kick off the next one and the next. Then we review the work of each as they come through. It's just CPU pipelining for human workflow.
The process is far from perfect but the throughput is very high. The limiting factor is review. I spend most of my time doing line-by-line review of AI output and asking questions about things I'm unsure of. It's a very different job from the way I historically operated, which involved tight code -> verify loops of manually written code.
At my company (Charlie Labs), we've had a tremendous amount of success with context awareness over long-running tasks with GPT-5 since getting access a few weeks ago. We ran an eval to solve 10 real Github issues so that we could measure this against Claude Code and the differences were surprisingly large. You can see our write-up here:
Often, our tasks take 30-45 minutes and can handle massive context threads in Linear or Github without getting tripped up by things like changes in direction part of the way through the thread.
While 10 issues isn't crazy comprehensive, we found it to be directionally very impressive and we'll likely build upon it to better understand performance going forward.
The company I work for generates thousands of these each week for children's personalized storybooks to help them learn how to read. The story text is the core part of the application, but the personalized images are what make them engaging.
That's very interesting. I would have assumed that 4o is internally using a single seed for the entire conversation, or something analogous to that, to control randomness across image generation requests. Can you share the technical name for this reasoning process so I could look up research about it?
In my experience, AI isn't very good at debugging AI-generated code. If it fails to make the right insight, it loops continuously until it's completely off the rails. I'm surprised your friend hasn't fully gotten stuck with this, as it seems like a huge risk for his startup.
> I fine-tuned GPT-4o to turn Claude's sketch of changes into a git patch, which would add and remove lines to make the edits. I only finished generating the training data late at night, and the fine-tuning job ran as I slept
Could you say more about this? What was the entirety of your training data, exactly, and how did the sketch of changes and git patch play into that?
I wonder if the script can be flipped to both encourage the use of ChatGPT and scrutinize its output among students. I imagine that analyzing the results of ChatGPT output for something like a routine essay prompt requires a higher degree of precision and subject-matter expertise than writing the essay itself.
How much time do you give candidates to complete their work samples? I'm curious whether work-sample tests filter out, say, parents with young children, in which a company with a 4-6 hour technical interview might be preferred over an unbound take-home assignment (in addition to the possibility of more interviews).
The girl from the creepy ex-girlfriend meme actively capitalized on her stardom. It seems that the sociological phenomenon of involuntarily going viral is becoming more well-understood.
Are sign-ups intended exclusively for people listing their gear? Perhaps you can have sign-ups for people trying to rent, too, and request additional information that would help you hone the site, such as equipment sought. For example:
Equipment Sought: <text field or drop down listing camera lenses>
This could be done under the guise that you will send them an e-mail notification when the requested equipment is posted to the site. This would help identify whether:
1. Users are camera-savvy at all or are indeed random people "stumbling" upon the site
Nobody I know is capable of standing for an entire workday. A drafting stool is absolutely required, and it's often the trickiest part of the configuration; for men taller than six feet, it's very difficult to find an inexpensive drafting stool that is sufficiently tall to match the height of your desk.
Preparing well for your interview and applying directly is much more efficient. I'm sure most entrepreneurs want to salvage they're failing startups and are eager to quit for the next venture as soon as the opportunity presents itself.