In your experience using your plugin (and the other tools that do something similar like herdr), does it make doing a larger volume of work feel more manageable?
In my experience thus far, surfacing/managing session state is only part of the issue, context switching between them is another entirely and feels like the real productivity bottleneck for me
If you're truly multi-tasking with this type of setup it feels more like "tiktok coding", "brainrot coding", or any other term that should be used for it.
I'm pretty sure we're moving away from it, the agent you interact with via voice or typing will go to a higher and higher abstraction level, and you won't have to effectively micro-manage them.
The under-performers and coasters just don’t read their code, in my experience thus far it’s been pretty transparent.
PRs aren’t a perfect gate, but they’re one of the only ones we have right now, and it’s pretty clear who’s putting in the effort and who isn’t.
A thought I’ve been chewing on regarding this….
What if “what do we get out of this?” was built into the tool that we use?
Something like a personal agent that you carry with you from job to job and that accumulates capabilities along with you?
Getting exposure to more and different work could become something that you get a real, tangible benefit from.
That would require technology that hasn't yet been created to be created. Tbh I'm happy with just having enough token spend to use on side projects for now.
I recently used clause code to help me learn nix + home-manager!
For anyone considering it - it’s been fun, genuinely useful in my day to day, and I can’t recommend it enough - I now have a source controlled tool kit that I can take with me anywhere I go
2cents from a kid who grew up in a NASA family during the shuttle years -
As others have commented, NASA’s baseline objective is to not kill astronauts.
My understanding of their ethos growing up was that there was absolutely no excuse not to pursue excellence and prioritize safety when people’s lives were on the line.
One would have to think that goal is fundamentally incompatible with SpaceX’s way of doing things (see the many exploding rockets - who wants to get in that?).
And from what I’ve read and heard through the grapevine, working with SpaceX as a contractor on Artemis has certainly had pain points related to these mismatched priorities.
SpaceX has the most reliable orbital launch vehicle ever made. Falcon 9 block 5 has had 550 successful launches out of 551 attempts, giving it a 99.8% success rate. For comparison, Soyuz-2's success rate is 97%, Ariane 5 is 95.7%, and the Space Shuttle was 98.5%. All of these are worse than Falcon 9's block 5's landing success rate of 98.9% (552 out of 558 attempts[1]).
The current Starship launches are part of a development and testing program. They expect quite a few failures (though probably not as many as they've experienced). But since each Starship launch is only 1/25th the cost of an SLS launch, SpaceX can afford to blow up a lot of them. And they won't put people on them until they have a track record of safe operation. Falcon 9 didn't have crew on it until the 85th launch.
1. The number of landing attempts is higher than the number of launches because Falcon Heavy results in multiple landings per launch.
You risk it when there are no people on board to find the issues. Fix issues, rinse repeat.
NASA/Congress pushes the armchair quarterback approach. Analyze forever, fail because analysis isn't the same thing as real world experience, get stuck using 50 year old rocket technology. Each engine on SLS cost more than the entire Starship super heavy launch vehicle.
By weight the RS-25 engines cost about 70% of that of building their 7000lb mass dry mass out of gold. That's insane.
NASA says its baseline is to not kill astronauts and yet it is currently planning to send astronauts on a mission in space with an Environmental Control System on its first space flight in a capsule that has flown in space once, and was different on that one flight, and had unexpected heat shield problems with another different heat shield and on a untested return path that is guessed to fix the issues. Actions speak louder than words.
I don't think so, because both losses were due to bad management decisions under irrational political pressure, not any lack of engineering knowledge that more unmanned testing could have provided.
Challenger was lost because NASA ignored a critical flight risk with the SRB joint O-rings. And by "ignored", I mean "documented that the risk existed, that it could result in loss of vehicle and loss of lives of the crew, and then waived the risk so the Shuttle could keep flying instead of being grounded until the issue was fixed". They didn't need more unmanned testing to find the issue; they needed to stop ignoring it. But that was politically unacceptable since it would have meant grounding the Shuttle until the issue was fixed.
Columbia was lost because NASA ignored the risks of tile damage due to their belief that it couldn't be fixed anyway once the Shuttle was in orbit. But that meant NASA also devoted no effort to eliminating the risk of tile damage by fixing the issue that caused it. Which again would have been politically unacceptable since it would have meant grounding the Shuttle until the issue was fixed.
Wrong. Both were lost because of a fundamentally BAD ARCHITECTURE. And that architecture was bad because the NASA engineers who designed it, had never designed anything like it before and were never able to test or evaluate any of their assumptions.
Columbia would not have been lost if the Shuttle was top stacked, instead of side stacked.
Challenger would not have been lost if not for the use of solid rockets to launch humans.
Both of these design decisions were done to reduce development effort.
No, I'm not wrong. We're both right. Yes, the original decisions on the Shuttle design were braindead. But even given that, the decisions to ignore clear red flags from Shuttle missions were also braindead.
Agree. But I think that Shuttle didn't do intermediate tests of these things is part of the reason it never lived up to its potential. During development they lost fact of what they tried to achieve in the first place.
They sacrificed what worked for potential, but tried to take far to big of a step.
I would argue, if you design something that has so many potential pitfalls and so many operational constraints, and so many drivers that make it incredibly expensive and slow, it is understandable why they started overlooking red flags. They would have barley ever lunched at all if they had not overlooked red flags.
> They didn't need more unmanned testing to find the issue; they needed to stop ignoring it.
Should such testing have been needed? No.
Was such testing needed, given NASA's political pressures and management? Maybe. Unmanned testing in similar conditions before putting humans on it might've resulted in a nice explosion without loss of life that would've been much harder to ignore than "the hypothesizing of those worrywart engineers," and might've provided the necessary ammunition to resist said political pressures.
> Unmanned testing in similar conditions before putting humans on it might've resulted in a nice explosion without loss of life that would've been much harder to ignore
The loss of the Challenger was the 25th manned orbital mission. So we can expect that it might have taken 25 unmanned missions to cause a similar loss of vehicle. But what would those 25 unmanned missions have been doing? There just wasn't 25 unmanned missions' worth of things to find out. That's also far more unmanned missions than were flown on any previous NASA space program before manned flights began.
Even leaving the above aside, if it would have been politically possible to even fly that many unmanned missions, it would have been politically possible to ground the Shuttle even after manned missions started based on the obvious signs of problems with the SRB joint O-rings. There were, IIRC, at least a dozen previous manned flights which showed issues. There were also good critiques of the design available at the time--which, in the kind of political environment you're imagining, would have been listened to. That design might not even have made it into the final Shuttle when it was flown.
In short, I don't see your alternative scenario as plausible, because the very things that would have been required to make it possible would also have made it unnecessary.
Record low launch temperatures are exactly the kind of boundary pushing conditions that would warrant unmanned testing in a way that not all of those previous 25 would have been. Then again, so was the first launch, and that was manned.
> I don't see your alternative scenario as plausible
Were not necessary to show problems with the SRB joint O-rings. There had been previous problems noted on flights at temperatures up to 75 degrees F. And the Thiokol engineers had test stand data showing that the O-rings were not fully sealing the joint even at 100 degrees F. Any rational assessment of the data would have concluded that the joint was unacceptably risky at any temperature.
It might have been true that a flight at 29 degrees F (the estimated O-ring temperature at the Challenger launch) was a little more unacceptably risky than a flight at a higher temperature. But that was actually a relatively minor point. The reason the Thiokol engineers focused on the low temperature the night before the Challenger launch was not because they had a solid case, or even a reasonable suspicion, that launching at that cold a temperature was too risky as compared with launching at higher temperatures. It was because NASA had already ignored much better arguments that they had advanced previously, and they were trying to find something, anything, to get NASA to stop at least some launches, given that they knew NASA was not going to stop all launches for political reasons.
And just to round off this issue, other SRB joint designs have been well known since, I believe, the 1960s, that do not have the issue the Shuttle SRBs had, and can be launched just fine at temperatures much colder than 29 F (for example, a launch from Siberia in the winter). So it's not even the case that SRB launches at such cold temperatures were unknown or not well understood prior to the Challenger launch. The Shuttle design simply was braindead in this respect (for political reasons).
> If those were unmanned test flights pushing the vehicle limits
As far as the launch to orbit, which was the flight phase when Challenger was lost, every Shuttle flight pushed the vehicle to its limits. That was unavoidable. There was no way to do a launch that was any more stressful than the actual launches were.
See my response to Mauling Monkey upthread on why the cold temperature of the Challenger launch actually wasn't the major issue it was made out to be.
Note also my comments there about other SRB designs that were known well before the Shuttle and the range of temperatures they could launch in. Those designs were used on many unmanned flights for years before the Shuttle was even designed. So in this respect, the unmanned test work had already been done. The Shuttle designers just refused to take advantage of all that knowledge for braindead political reasons.
Testing wasn't really the issue with the loss of the two shuttles. In both cases, it was mostly a management issue. For Challenger NASA had seen o-ring erosion in earlier launches, and decided it was not a big risk to the crew. Then they launched Challenger against the recommendations of the engineers in charge of o-ring seals. For Columbia, they has seen foam strikes in earlier launches, but since they had not caused catastrophe in the past, they decided that foam strikes were acceptable. Even when it was clear that a large foam strike had occurred on the launch of Columbia, management wasn't concerned enough to try to get ground-based images of the shuttle to check for damage. Could Columbia's crew have been saved had they known the extent of the damage? No one can say of course, but not even trying to do everything possible was inexcusable.
They very nearly lost the first shuttle they launched. Jumping straight into manned testing was quite reckless, but politically necessary. If they had tested the shuttle without crew, that would have gotten people thinking that crews probably aren't necessary for a lot of shuttle missions, in particular launching satellites. It also would have prompted people to compare the cost of shuttle launches to other unmanned rocket launches, in particular for commercial satellite launches (which they were doing until the Challenger disaster.) These are comparisons that would have been very problematic for NASA as a political entity.
> They very nearly lost the first shuttle they launched.
Which mission are you referring to?
If it's STS-1, AFAIK there were no close call incidents during the actual flight, but the mission commander, John Young, did have to veto a suggestion to make that mission an RTLS abort instead of an actual orbital flight. Doing that would have been reckless, yes: Young's reason for not doing it was "Let's not practice Russian roulette."
The overpressure caused by the SRB ignitions exceeded predictions due to the geometry of the launch pad. This overpressure forced the orbiter's bodyflap away, beyond the design limits of the hydraulic system that controls it. John Young said that if he had known this, he would have ejected, which would have caused the loss of the shuttle.
Ah, I see. But in fact the body flap was not inoperative, and the Shuttle landed safely. So this looks to me like a case where Mission Control turned out to be justified in not telling the crew what had happened.
One thing I wonder about is whether it would have been possible to test the flap while in orbit, to see if the hydraulic lines were actually ruptured or not.
They made the right call, kind of, and only by accident. John Young had telemetry for the flap available to him in the cockpit but didn't notice it happen at the time. NASA ground control also had the telemetry, but also didn't notice / understand until after it was too late to eject (which was only possible during a narrow window for ascent, and not at all for reentry if the body flap had been inoperable.) They also simply got lucky the hydraulic system performed beyond it's designed safety margin.
The problem there is the Shuttle was deliberately designed so it couldn’t be flown unmanned, which risked lives and wasted money for lots of simple satellite launches.
We all know the value of a project like Voyager - if the US government fails to support it and it puts the mission at risk, do any pathways exist for this to become a publicly stewarded project?
Have there been any other major government projects that have transitioned to either private or public ownership?
Yep, it’s all totally pointless so why bother thinking and dreaming of a way out, right?
Even if the ideas in this post are a little unrealistic in the face of modern convenience, it’s productive to talk about it.
Is there something else we should be doing instead?
