Olscore

Everybody is converging on similar ideas, but the execution isn't super clean in a lot of "software factories" popping up. Coordinating through shared written state becomes obvious once you build something complex enough. Anyways, I have been building Pullboard (open source). The original concept came from needing agent coherency on a very complicated project.

https://github.com/pullboard-dev/pullboard

Building a house has three layers:

1. Vision: what we want (our intent)

2. Blueprint: the spec we wrote (our design)

3. Inspection: checking what we built against the blueprint (the proofs)

This research makes the inspection close to perfect. But an inspection only checks the blueprint, not our vision, so a house built from the wrong blueprint can still pass a perfect inspection. The other half is making sure the blueprint matches our intent and stays that way while agents build. I'm working on that, so I think this is complementary:

https://github.com/pullboard-dev/pullboard

The author is wrong, and a software factory isn't a distraction.

People are thinking about this from a quantity angle, but the key is quality, and achieving a self-maintaining project at home. I built a distributed trading system that runs multiple strategies in US options and MUST be correct. So my goal wasn't to build huge quantities of software and pump out garbage, but to ensure correct behavior and proper fixes in the codebase with agents.

Open sourced my methodology: https://github.com/pullboard-dev/pullboard

Yes > real issues are in this layer of intent

This is why code is going to be automated, and the software engineer is a link between organizational intent and the code. This is what I’m working on.

Do they matter? Yes. Should you use them? No. (Mostly)

This is going to be opinionated from an extreme "vibe code" viewpoint, but I think the future is "GAD" Governed Agentic Development. Designing constraints that agents must follow, and therefore different forms of frameworks. What the agents need is lines in a coloring book, the human is responsible for drawing those lines. So frameworks of the future should be focused on constraining an agent to develop properly, or designing what is and is not permitted.

Building Autonomously, Open Source: https://github.com/pullboard-dev/pullboard

My open source approach: https://github.com/pullboard-dev/pullboard

Most days I am capable of running 15-30 agents across 5 projects; if I had the budget it would scale. Pullboard is more of a methodology, and looking at the components alone does not reveal why it works. It's not just "orchestration" it's more like a coherence, outcomes and judgement over time.

You are correct that it can all be correct in one sense, and wrong in the product (“what the user wants”) sense. Of course you need to monitor the output, that’s a given. You need to question the entire system. That is the frontier for engineers.

“How is the agent lying to me?” Etc.

About 25-30% of the things shipped by agents need fixes.

It's cute, but my goal is building serious projects autonomously.

https://github.com/pullboard-dev/pullboard

Been using the Pullboard workflow to build software that MUST be correct, and recently open sourced it. There was another HN link today involving agents role-playing and I can't take that seriously, no offense. (Love fun projects like this, seriously, it's cool.)

From my perspective, agents are great, they code better than most of us. But like all of us, they also make many mistakes or can't see how their changes impact the codebase. But that is a test-driven development mitigation along with some sort of scrutinizing process, "prove it". I'm actively working on this, and by actively working on it, I mean building serious apps that hit correctness walls, figuring out why Pullboard didn't catch it. To me, this is all about the process.

Haha. Locally it was passing. That badge is GitHub running the tests on its own machines, where a couple of new browser tests fail. Fix is going through the same loop: one agent fixes, another verifies, then it merges.

Interesting seeing other people's approaches to orchestration.

I've been working on Pullboard and just open sourced it: https://github.com/pullboard-dev/pullboard

To me, orchestration is not really the core problem. The bigger challenge is handling agent coherency over long periods of time, (drift) so my solution is a living forum-like system where agents shout to one another, document work in items, and follow doctrine handed down by the developer and work against a known specification that's checkable. I have used this workflow in several large projects that MUST be correct, and it works for me. Currently cleaning it up for other users.

What else would you call students voting for loan forgiveness? Point blank the candidate is effectively saying, "we will give you $xx,xxx" in the form of loan forgiveness. It is the same for healthcare. This is a literal voting for benefits; and, this creates perverse incentives for the electorate to vote for whomever will "pay them" the most for their vote. Candidates are simply buying votes by offering free stuff with taxpayer monies. It is completely broken at this point with one candidate trying to out-give the next.

Fundamentally, it is disgusting we are forced by government to buy insurance products (e.g., car, health) provided by for-profit companies; however, I do not support universal healthcare either. The government has zero ability to control its expenditure, because the electorate vote themselves benefits.

The long-term financial incentives to maintain a functioning society are all broken because of the misaligned short-term (vote for me, get free stuff) and long-term incentives (debt reduction, financial management, business planning and other investments.) Voters are simply looting the treasury at this point. It is a shame. I cannot believe anyone actually buys into the notion that government will fix problems, or somehow do a better job than what already exists.

The candidates are just handing you money from your own pockets, and skimming off the top.

It's so damn dumb.

Neat product, we rolled something similar to this using Slack where we manage the phone system, etc. I especially like how you can reply within Slack and text back the customer. Seems like your major problem with this startup is usage costs as text messages and phone calls can quickly add up. We are a small team of ~7 people and our monthly Twilio expense is twice your price here. I.e., not priced high enough.

I might prefer this product with a slight change: instead of trusting you my business phone number, maybe I could simply point my Twilio endpoint to your servers? That way you are not soaking up passthrough costs of customer usage; plus, I don't have to worry about getting my number from you after all my customers are familiar with that number. Anyways, it's a neat concept. I have provided our phone system to other businesses and can totally see the value in this product.

There's no need to fit the post into a larger narrative; it is what it is. Seems more like you may be projecting your psychology or fears onto the article. It's just a list of pricing psychology tricks. And it cuts both ways you know; readers learn how pricing strategies may affect their buying decisions.

The article is not advocating for the "manipulation" of anyone. It's up to the reader to implement, ignore or consider. If the title and some words were rephrased it could be an article on how to spot pricing tricks; the content would mostly be the same.

It's you.

Your last question is loaded; it assumes maximizing profit is bad. In practice high profit margins are often a reward for being first to market. Maybe those high margins are a recompense for R&D costs. Plenty of answers to rebuke your suggestion that maximizing profits is unethical. It's also a situational topic made more nuanced by the specific product, company and many other circumstances.

> get less than zero sympathy if they talk about having difficult lives

You just proved this part.

Except the Regressive Left is doing a good job proving they aren't all that open minded. The new liberal coming out of college campuses from safe spaces is not open minded at all. So perhaps in the past Liberals could make the claim of open mindedness, but not today. Especially when conservatives are banned from speaking on college campuses, not to mention being banned from social media.

Yep. I received a similar score (73% liberal) and consider myself in-between Libertarian and Conservative. The test is totally bogus.

Then we can argue about the definition of safe, or the reasonable expectation of safety. But it seems that Hacker News would rather point to one example which apparently "invalidates" the claim "handily". What do you consider safe then? If you are determined to argue based on one example; Do you not take a risk starting a business? Do you not take a risk eating foods? Do you not take a risk driving?

There are reasonable mistakes made in the course of living and of any action. So if you want to exaggerate the claim of one (or even a few) examples to the point of making it appear as an epidemic in America; then I will hold you to a higher standard than the half-assed arguments that I see here. Many people engaged with these narratives are grossly misrepresenting legitimate claims of police brutality or racial discrimination. If you cannot be honest in debate, then I would also not expect the same to be honest in any proposed solution. Blatant misrepresentation by so many; it's disgusting.

You going to base an entire argument on one example?

Your comment shows the level of misinformation and reputation damage done by media and various social movements. America is safe for all law-abiding persons. Not only do I disagree with your comment, but I find it offensive that you would propagate the myth. It's damaging and unsubstantiated.

> I think Facebook is here to stay.

Well, that just sounds like an open invitation to challenge them.

One of the last consumer-facing, blockbuster level startups outside of SV (or California) that comes to mind was Groupon. But I don't consider them to be that great; kind of a fad that took off for a while and is now lingering. When I say blockbuster level startup I mean something that becomes a household name used by mostly consumers. Highly visible companies mostly. I lump LA/SV together because they're in the same state, and there seems to be a lot of inter-funding between the two areas. But I'm also from Chicago so maybe it's just me. Hah.

Snapchat obliterated Facebook's news feed with the younger generations under 25. Status updates are now Snapchat stories, and news feed items on Facebook are more like life milestones. So I think it changes the way younger demographics use social media. It definitely encourages a lot more trivial sharing of activities throughout the day with others.

Silicon Valley hasn't released a blockbuster app, website or company in a while. Particularly social media companies that upend the rest of the world and the way it functions. The directly consumer facing / social companies really move perception versus other companies that don't interact with the general public. There was also the iPhone 2007 which changed the way the entire world used their phones, and a lot of fallout change with it. I think the media attention seems to have lulled a bit since there haven't been what I'll call blockbuster techs in a while; e.g., some large consumer facing company that changes people's lifestyles. So maybe the glamour is missing. The amount of attention SV received a few years ago seemed to be bigger, with everyone eagerly awaiting new life changing tech that is as obvious as the iPhone, FB, Instagram, YouTube or other very consumer facing and widely used consumer companies.

Seems like Uber and Snapchat were the last game changing companies for how people interact with the world via tech on a large scale. IMO it's lack of media attention, excitement and companies that are very obvious lifestyle changers.

Sorry. I understand the sentiment behind this but disagree with advisory or demands to speak a certain way. It's blatant political correctness and nobody has an obligation to set another person's expectation regarding coding. In common vernacular we say something is easy as an attempt to encourage a person to continue. This would just be changing words in order to achieve the same goal. What difference does it make if some say it's easy and others say it's hard? Let the dynamic range of opinions be. Is it necessary to squash one opinion over the other in an attempt to soothe the struggling of a few newbies?

Cryptocurrencies are digital tokens. Ownership of these digital tokens are kept in a ledger called a blockchain. Every transaction or transfer of tokens is recorded in the blockchain. Everyone can also see the blockchain as it is a public ledger. Both Bitcoin and Ether are cryptocurrencies. Bitcoin was the first to demonstrate blockchain technology. In practice, these tokens function like programmable money. However the usefulness of Bitcoin is limited. Ethereum was developed to expand the original concept so more things could be done with these digital tokens. Ethereum made the programmable tokens more powerful with features like smart contracts. It is worth noting that each cryptocurrency has its own blockchain which can be confusing.

DAO is an autonomous corporation that runs on top of Ethereum. The digital token in the Ethereum ecosystem is called Ether. So the DAO raised somewhere around ~$150M USD in equivalent Ether funds during its IPO-like phase.

Real time chart for DAO/BTC (Down 41% currently): https://poloniex.com/exchange#btc_dao

If this were to actually happen I would consider it bad news for independent journalism and dangerous for some political viewpoints, even in the United States. Google already owns one of the largest social media platforms: YouTube. Both Twitter and YouTube have pretty large political significance and being owned by the same company could be an issue. Especially as we have seen some persons lose their verification badges (on both YouTube and Twitter) for allegedly being on the wrong side of the political spectrum. The idea of this makes me uneasy.