- It's extremely verbose and often incomprehensible when doing even basic tasks. Like it'll write a giant jargon-filled essay then end it by asking for a judgement call on something that references its own convoluted jargon.
- You can ask it to do research on a topic, and it'll just straight up be lazy, pretending it's really digging deep to find stuff when actually it's just grabbing cached SEO snippets off a search engine.
So, we could technically debug a prompt's output? I get that there are too many steps to actually step thru, but what if there were checkpoints? At least you could isolate behaviors to specific sections of a neural network?
Well it's a transitional methodology during the early stages of a major shift in software engineering. Just look at what almost everyone is complaining about with AI coding, and then the inadequacy of their proposed solutions - this is just begging for new tooling that we'll probably consider obvious in a few years.
It's clear to me now that the lack of benchmarks for competence in this space means everyone thinks they're geniuses who don't need a better process, because apparently their workflow "works for them."
Not sure what to say to any of this, because it's not even really related to the article except to say the assumption is supposedly completely wrong. That doesn't make sense to me, because as soon as AWS or something important goes down everyone immediately blames vibe coding.
So which is it? Is process completely solved here ("just get gud"), or is coding with agents causing problems?
Thanks, yeah I just went with the most controversial term as the catch-all which just means: you prompt an agent as your core workflow.
For me as well, I do projects for clients that would have taken me months, and I deliver them in a fraction of the time. It's amazing and totally helped cure my burnout (which I had for over a year before I found Claude Code.)
I'm making the case that we should make tools for the higher abstraction, not a lower one. You said it yourself: why should we read/write binary? We don't, we shouldn't. It might be useful in some cases, but working with assembly is much easier.
Intent is more natural to us than code, for the same reason assembly is more natural than binary.
I'd agree with you then! I don't think that case was clearly laid out (or at least I didn't understand your argument to be as such). I'd also say that humans are historically quite bad at communicating intent (even if it comes more naturally and is communicated in natural-language), so I think tools that support human <> agent interaction and iteration are important.
I never said you have to turn your brain off to feel the limitations.
Actually, for more complex work I think it's pretty common to spend a long time crafting some elaborate prompt, and then arguing with the agent for 10-20 turns, getting a "passable" plan, accepting it then arguing with the agent every step of the way because it's doing it wrong. It's incredibly frustrating, even with models like Fable.
Even after that, I'll often find out during later sessions that some feature that was supposed to be deprecated was actually silently left in "because I wasn't sure you wanted it completely gone" or something.
I agree that exploring a codebase through prompts is actually quite nice! But the mental model you get from that is almost always warped - you have to supplement that with reading the code, where 9 times out of 10 you will find some kind of discrepancy that you're unhappy with.
Your experience is night-and-day from mine. Both myself and the AI correct and remove each other's gaps in understanding. There is never what I would call arguing. Disagreements are resolved by back and forth discussion and reaching consensus.
This sounds like not the best workflow. If your prompt is that long, you may not be spending your time very efficiently.
Splitting problems into smaller problems is huge. You want a concrete idea that you still own. Only tell an agent to do something you know it can nail - this will likely be one subsystem. The subsystems and how they talk is on you.
I agree, I tend to give a high-level concept for what I want done first, and then break it into smaller tasks. That said, there's almost always a misunderstanding within the smaller tasks anyway, which I have to test to find out about, then ask the agent to fix.
This does not match my experience at all. I use Fable as an orchestrator, and describe the end goal I want to achieve. It investigates the current state of affairs, and determines the smaller work units needed. We discuss each one, and eventually ticket it out in Linear. By that point, each ticket has all the relevant details, scope, decisions and acceptance criteria.
Then I have it write prompts for implementation agents based on the ticket. These agents are almost always Opus, except for the most complex issues. The prompts contain broader contextual details (like what other tickets might be worked on in parallel, the boundaries, operational/environment constraints, and so on). Each implementation agent starts in plan mode and uses a skill I created called "super plan". Super plan has the agent write the plan and then have it adversarially reviewed by three subagents, and hardened based on their feedback. I then read that plan and greelight it. Once the agent is done with the implementation, it then uses three subagents to do a code review of different aspects (like test quality, regression risk, security, etc.) and incorporate the changes. Then it does a live QA in the browser (if there are UI changes) to make sure the feature has good UX and the UI works as expected at different breakpoints and so on.
Then the Fable orchestrator does one last code review and gives a ship/no-ship verdict, along with a 1-10 rating.
This works incredibly well, and is almost completely hands off. I make all the major decisions and review the results. I never find myself "arguing" with the orchestrator. I might sometimes get frustrated at the implementation agent but that's mostly for UI fidelity issues and honestly pretty rare these days.
The control room in Jurassic Park was honestly beautiful - and something about those shaving cream cans really crystallized the aesthetic for me, weirdly. I had no idea that it was taken so seriously, I just remember thinking "damn, that's actually pretty realistic" when I re-watched the movie a few years ago.
It's still pretty experimental, but I think now that AI can feasibly generate code from intent/specs it's worth doing... especially with how much vibe coding is both a blessing and a curse.
Basically, what if we took those markdown specs everyone likes using and systematized them into a model graph, anchored claims to code, then represented that as a wiki? And what if we surfaced a planned change to a codebase as a diff of the definition of that model? You can then properly keep track of what gets implemented and how, because you're no longer reading an essay from the agent as a plan, you see a complete diff of everything it plans to do.
I've been using it myself for work, but it'd be nice to get some feedback from other people's perspectives.
I don't understand why the mainstream is celebrating the total collapse of any meaningful political opposition to populists. This kind of fluffed-up 2010's style optimism campaign is exactly how the establishment lost control in 2016 in both the US and the UK.
I think it's sad that Binface is the only one even attempting to engage in democracy at this point. He's a satire but he's also, seemingly, the only legitimate opposition that populists face. That should be concerning and embarrassing, but no one has learned anything over the past 10 years.
So, what happens when Binface loses? Are they just going to try to put Farage in prison like they're doing with the other populists? That'll surely help.
And if he does somehow win, what then? Doesn't that also prove that populism is the only viable strategy? Either way people are celebrating their own defeat.
The other parties aren't standing in this particular byelection because they (correctly) realise that it's just a media stunt by Farage, who is attempting to paint himself as a victim of establishment harassment (while being the epitome of 'the establishment' himself). By not standing, and forcing Farage to run against joke candidates, they've made a fool of him (which generally harms populists more than anything else you can throw at them).
The other parties have all said that they will run candidates against Farage in the almost inevitable second byelection that will by triggered later when parliament finishes its investigation into his corruption and punishes him for it.
This doesn't make a fool of Farage though! It clarifies to anyone already skeptical of the establishment that when pushed, they'd rather not play than risk losing. This is literally self-defeating!
You claim that this kind of thing "generally harms populists more than anything else," but I can't think of a single time that it actually has at the scale that matters. What would harm populists would be a viable alternative that takes the concerns of the population seriously.
If Farage wins he is still subject to an investigation that could eject him from Parliament, over a 5m crypto gift/loan he received from an ex-pat donor that he did not declare.
Farage is looking to get a popular mandate to try and both draw attention away from that investigation, and justify keeping his position because "the people have spoken". The other parties don't want to undermine the investigation by taking part in an election which would be moot if he were found guilty anyway.
Farage is therefore punching on air, and has been reduced to arguing that a joke candidate with a bin on his head who claims to be from outer space is an "establishment" (aka "deep state") plant.
It's actually a smart move from the other parties. Without a serious "enemy" to fight, populists look foolish as their usual rhetorical moves have no bite.
> If Farage wins he is still subject to an investigation that could eject him from Parliament
He will win, of course.
But Parliament can't actually eject him. All they can do is enable the one mechanism that could: a constituency recall petition that needs 10% of his electorate to sign it, that triggers… a by-election he could lose.
If he runs and his constituency vote for him in that, he's their MP.
That is true, but while he is popular in his home turf, 10% is a low threshold for a figure as divisive as Farage, so seems pretty much inevitable, unless this pre-investigation-results by election kills the motivation.
Now would he win the second by election even with a finding of misconduct against him? He might very well. But the establishment parties (especially the Tories) will feel much better placed to challenge him if they have him being found to have conducted in dodgy behaviour.
If Farage wins, things continue exactly as they were: Farage the MP of Clacton, being investigated for undeclared financial gifts. With no serious counter-candidates, even getting 99% of the votes would be completely meaningless.
If Farage loses, well, he'll have lost to a bin, meaning his political career would be finished.
And anything besides a massive victory would only hurt Farage. Prior to this he was seen as a likely future Prime Minister. If he gets a 55/45 victory against a bin in a constituency which heavily favors his party, who would ever take him serious?
If the other parties contested the election, they would've legitimized his stupid "I'm getting a mandate from the people" move, automatically making it way more of a mess if his undeclared financial gifts turned into being expelled from the House.
The only winning move is not to play. The other parties know this, and by treating the Count as a completely legitimate candidate the media are guaranteeing this.
I lived in London for six years starting just before Brexit, so I watched this exact confidence up close. The British public "knowing" Farage is damaged is not new, it's not justified, and it doesn't do anything except make people feel better on social media.
I'm pretty sure that just like every other backhanded attempt to squash the populists, this will backfire. I can't know that of course, but I'm pattern-matching against years of this kind of stuff happening in like 5-6 different countries in Europe already.
He is noticeably more damaged now, believe me. Everyone thinks this election was at least a stupid idea and it is his stupid idea designed for his personal benefit.
You are right that it could backfire, but to give you a much longer and more analytical answer, here is the picture as Farage understands it and why he did what he did:
- Farage is the leader of an insurgent party with the ability to command national media attention. He can make the main news channels attend.
- He was already MP with a large majority off a pretty good, recent turnout.
- There is no local media at all to speak of — no local newspaper worth a damn, no local TV, no other earned media
- The election is five or six weeks away.
- No national party can stand up an adequate candidate in a parliamentary constituency election in that time. It will be novices, first-time candidates with poor name recognition.
So the above is the election he wanted to fight, right?
If any of the main parties stand up candidates, they will all feel they have to contest it so as not to lose vote share to Farage, and Farage wins.
If nobody stands up, Farage wins.
And if a novelty candidate stands up, Farage wins.
Whichever way, the outcome after the by-election is the same as the one before: Farage is going to be the MP for Clacton. So given that this happens regardless — it cannot be stopped even though he started it for his own benefit — what is the best outcome for people who wish to see Farage politically damaged?
It is not the first one, because that is the specific outcome Farage wanted.
This way he now has to campaign around the simple story: he is fighting for his political skin, and his main campaign position to the people of Clacton (and deprived Jaywick) is that it's OK he's been given money and gifts by crypto billionaires and convicted fraudsters and that it's unfair for that to be investigated.
This is not at all a backhanded thing; it's open party politics. The last time this was done it was done to a fully establishment Tory (David Davis) who resigned to fight a by-election on a single issue.
He'll still be under investigation(s) when he comes back, and he won't be able to blunt the impact of those investigations by claiming that he has beaten all the establishment candidates. This is the best path forward.
This is all from the perspective of people who already oppose Farage, though. Supporters will zealously reframe everything as illegitimate attack. Soft skeptics will notice the establishment's overreach.
I agree this might be a normal political tactic on paper, but that's irrelevant when you're dealing with populism. The entire game is tribal framing. To anyone outside the anti-Farage coalition, this just looks like the establishment closing ranks, and that's more recruiting material for him.
What I can see happening here, at best, is maybe Farage stepping away if the pressure gets too much. But then you risk him getting replaced by a more angry figurehead who will use Farage's downfall as evidence of the "hatred and dirty politics" of the establishment.
> This is all from the perspective of people who already oppose Farage, though
Actually, you seem to be the one ignoring data out of partisan prejudice. The polls are quite clear Farage's shady finances are damaging both him and Reform.
OK but what I am telling you is that this has actually damaged Farage's standing in his own party and among his own supporters. There's actual evidence for this.
And I presented that scenario in the form Farage understands it. Remember: he literally started this.
If Farage steps down — he's done it before, and I agree that there is a very good chance he does so before the election — then Reform is finished. There is nobody else, even though a few Reform people like to excitedly tell you that Zia Yusuf could do it.
It's the same with Trump: who is going to take Trump's mantle with the same authority when he goes? Nobody.
But in the UK, the chances of a populist party appearing at the fringes and seizing real power is very much held back by the way our system works. Farage is a unicorn; incredibly rare. Even the Tory party would have difficulty seizing back populism for the next decade or two.
And there is no establishment "overreach" here at all. Farage is a democratically elected MP who is being investigated by the parliament he joined for things any other MP would be investigated for. He could just sit and wait for that to be done, because he's an MP regardless and the people who ultimately judge whether he keeps his job are his own constituents anyway. If political parties choose not to play his game on his own terms and timescales, that is a decision for each of them.
I think you are right that the issue is tribal framing.
The question is whether satire will puncture that.
Farage's supporters will be trying as hard as possible to paint Binface as a lefty establishment figure- but satire gives you an oportunity to reframe the debate.
Take the 5 million quid - the defence is it's a gift and who wouldn't take it if offered?
Binface can lean into that - rather than say it's terrible etc - he can say - yes I'd like a bit of that - and ask Farage how he can also get such a donation?
Such a question is in effect asking 'what do I need to do to get a 5 million donation' - which is the same as asking what Nigel did for it.
But it's more difficult to answer with 'none of your business' or I did nothing - implying Binface is equally likely to get it.
His zealots are already seen asking where the Count is "getting his money from", and implying that he is an "establishment deep-state plant".
But he's a bin, and it's his seventh election. You can't exactly ask questions like "where is a man pretending to be a garbage can getting the £100 filing fee from" without making yourself look incredibly silly. Everyone but the most extreme cultists can see that, even his own regular supporters.
You can't fight a bin. It's like wrestling with a pig: you just get dirty and the pig enjoys it. The real question is: is Farage's support strong enough to secure an overwhelming victory against the get-rid-of-Farage candidate without actually campaigning?
It's not a collapse of political opposition. The political opposition are simply not allowing Farrage to dictate the narrative here.
Whilst under investigation for undeclared funding, Farrage is trying to legitimise himself by resigning and having an electorate re-elect him at the expense of the tax payer. The mainstream parties have, understandably refused to play ball, leaving him to regain his existing position uncontested.
But, and this is the bit we are celebrating, Count Binface, a satirical figure, is standing against him, ridiculing him and highlighting in the media the whole selfish situation. This is a backfire for Farrage, as it has nationally pissed on his selfish legitimisation parade.
It's not that populists aren't facing opposition - it's that Farage resigned and said he'd be running in the by-election his resignation caused. He is using the by-election as a political stunt to try and get ahead of an incoming scandal - but by the opposition not running against him, he can't say that his mandate from the electorate is clear, and his only actual opponent is a (well spoken) bin.
Any amount of votes Binface gets is a deep embarrassment to Farage! Binface is just pointing at the farce that Farage has created, and undermining him in a particularly British way.
I think the strategy in leaving Farage to only face Binface is that win or loose it makes Farage look like an idiot. He wanted to get credibility back by getting re-elected after the recent scandal and this binface thing robs him of that.
There is no opposition in this round because it is a total farce initiated by Farage. It takes two to tango and no one else (other than Count Binface) is dancing Farage's Doofus Dance.
If Farage wins, he will face the inquiry he is attempting to escape by pulling this stunt (in a summer where the WC is happening, Farage managed to score the biggest and most protracted own-goal in the history of own-goals). An effect of the inquiry is that it will trigger _another_ election in which the other parties are expected to field a candidate.
I'm not from the UK so I don't know the proper terms/political procedure but if you read up on the whole situation beyond the jokes, what I said above is a good rough outline. This is hardly the death of opposition to populists.
I think the special case of the totally unnecessary by-election is important here. I would not expect the other parties not to contest the general election. I don't like the "X is an attempt to distract from Y" framing, but this really is a distraction from the "sudden revelation" that Farage has really dodgy financing.
Also, Farage is the ultimate "establishment" candidate. He would be the same level of obscurity as Tommy Robinson or Restore if he didn't have a regular seat on BBC Question Time. All of his money comes from a small number of rich donors. He's appealing to anti-immigrant sentiment in a constituency that has hardly any immigrants.
Specifically in this case, Farage is a celebrity populist; he is not likely to lose, and the political system (and the wider British public who oppose him) are conscious of not dancing to his tune.
He wanted this election on his own terms; he called it, to give himself a chance to bloviate and to claim that the very serious allegations against him are an establishment fit-up (when they are not).
The reality is that the outcome of those investigations has the potential to lead to another by-election (because only 10% of constituents need to sign a recall petition). Farage’s calculation is that if he triggers the by-election and wins before those investigations conclude, he can blunt the chance of a recall petition succeeding (and build some national case for Reform)
The response of the major parties to just decide not to play his game on his terms has some precedent. This is not an abdication of their responsibility, it is exercise of it.
More importantly this outcome is funny, broadly understood as a fair response, and is utterly humiliating to Farage, who is thin-skinned and easily enraged. He would have won against any candidate any party could rustle up at short notice and he knows it. He will still have his victory but nothing changes except that he is diminished.
- It's extremely verbose and often incomprehensible when doing even basic tasks. Like it'll write a giant jargon-filled essay then end it by asking for a judgement call on something that references its own convoluted jargon.
- You can ask it to do research on a topic, and it'll just straight up be lazy, pretending it's really digging deep to find stuff when actually it's just grabbing cached SEO snippets off a search engine.