philipp-gayret

I think it's a very exciting time and I am enthusiastic about it. What I tried to do is automate as much as possible of that decision-making, guidance and taste. Having said that, it is significantly more context switching, my solution so far is to have agents run longer autonomously, less interruptions is less switching. Prerequisite is that you must build a system first that lets you automate that, which is often very personal; most tools don't particularly apply.

I'm curious in what is the value of this kind of solution. Having run my own software factory for just a week or two, I'm at well over 1000 agent jobs (; a more flexible variant of what a swimlane on a scrum board represents). If I did a year of having the factory running, I would end up with 10~50K tickets across my repo's, then what? Do you keep them forever?

I don't follow what the value is in putting all that in a Git repo, let alone putting everything through a cycle of git/commit/push. The source of truth is the code, so if you're capturing this for additional context about why things were built, then you may as well follow the path of Entire; former GitHub CEO's company, and record the entire agent session to get the full context.

Is there not a great irony in over a weekend throwing Fable/Opus/Sonnet at your project, refactoring your whole codebase, and the purpose of that project is to teach people to use vi, git, sql and so on. Why would anyone want to learn that in the current day and age, when as you state it can refactor a project over a weekend fairly autonomously?

> So they are throwing out the maximum sentence based on the AI video asking for leniency?

It says:

> In sum, while the embedded “real” video footage of the victim was permissible, allowing the presentation of the AI video constituted fundamental error. And on this record, the judge’s consideration of the AI video so prejudiced Horcasitas as to render the sentencing procedure fundamentally unfair. Accordingly, we vacate the sentence for manslaughter and remand for resentencing.

Which is more or less; "AI videos of victims saying made up things should not be allowed at all.".

> And they also need to be built somewhere, and that place is probably best where electricity is abundant and/or cheap.

This is a Dutch website and here in the Netherlands we have demand issues. In these same areas where issues exist, data centres are being planned and built. There are waiting lists now for normal businesses who want a new connection to the net, or connections with more capacity. These are lists waiting for capacity to become available: The demand on the current net is already too high.

As it's relevant to the sport I practice and just came back from armwrestling training I'd like to randomly comment: Armwrestling clubs have a LOT of people with tendon pain and injuries. The general approach to recovery and building tendon strength (beside lifting heavy) is to do static holds of 10 seconds+ of light to medium weight. Often paired with very large sets (50+ reps) of _extremely light_ weight; lifting almost nothing, just to get the blood through the tendon. You should not feel sore at all in either movement. The idea being that blood gets into tendons through movement. As for static holds; tendons expand during these static holds, so the idea is that they can then absorb more nutrients... Or something like that; I'm no expert by any means!

In the bouldering community there has also been a bit of an uproar where Emil Abrahammsson (find it on Youtube) did very light static holds 2+ times per day for ~30 seconds if I recall correctly for great tendon strength, this also had some influence on how people train for armwrestling. This style was nicknamed "Abrahangs".

Anthropic's Claude fingerprinting technology at work; randomly inject "real" everywhere. If it was Codex you would have seen load-bearing choice.

Although that may be true, the quota at least on GitHub depends on what you're quering. We worked directly with GitHub and a complex enough organisation hit with a GraphQL query can actually hit your hourly app limit before you even get a response.

As for GitLab, having hosted it for medium size organisations (~200 devs) and seeing how monorepo's work (they don't, we had GitLab's team show us that one page view made 50K db queries on our setup), please consult with your local admin team before firing GraphQL at it.

Have they reported on the wiki case yet, or whether it even was even OpenAI internal? I'd expect that to fit the criteria for a "Larger Investigation" as per the framework.

I agree but your taste in making solutions, or that of your organisation may be very different from what an LLM does by default. I personally use specs to capture this taste; an example shared by most LLMs is that they like to document not only what they have built but also what they have not built. Especially after changing solutions or small migrations. Specifications can resolve most if not all of that behaviour.

Be sure to spend them! Another great feature of OpenRouter is that they will take your credits after a year. They just delete them. A ToS-legalized theft if you ask me. (Even if you are still actively using those credits.)

Not the first to discover that a rule file saying "please don't do X" is not permission management. Funny that she mentions it worked on het toy inbox but the real, large inbox ran into issues; The more context you add the less weight "rules" (instructions) have. Happens to the best it seems.

OP, I'm very interested in seeing an actual comparison ran through a common tokenizer of tool calls. I think you'll find different results than what you intended for this tool to be. You've mixed up tokens with characters on your screen.

Having spent too many years in CI/CD I'd agree but there is an even better solution; decouple deployments from releases. Make it possible to deploy without releasing, and release without deploying. (An implementation of this could be, for example: feature flags.)

> makes me concerned that you believe the only way someone would/could become more attractive is by performing some sort of charade.

I am unapologetically my authentic self, I find that works best. If you had broadened your horizons as you say; you'd find the same.

> you may just find that the people you think despise you and who you despise have some very good points, and the people who you thought were the only group you had anything in common with are actually quite toxic and full of bad advice.

There's no need to tell other posters what they think. As for women; I love women, and have always been in long term relationships. Maybe I'm just a lucky guy. I think it's odd though to try and appear superior to these groups as he does. You are right there are toxic people, especially those seeking to earn income and status off of male loneliness. I agree with you fully. Having said that, I stand behind what I said earlier.