Post B3btZWLZ8A1uFcM4hs by wolf480pl@mstdn.io
(DIR) More posts by wolf480pl@mstdn.io
(DIR) Post #B3ZzavwJfpgxK8gLDM by david_chisnall@infosec.exchange
2026-02-22T10:11:59Z
0 likes, 0 repeats
I have a new technique for reliably vibecoding apps:First, you write your requirements in an unambiguous specification language. This is the prompt, but to disambiguate it from less precise prompts, we will call it the source of truth encoding, or source code for short. You then feed it to an agent that will create an of outputs by applying some heuristic-driven transforms that are likely (but not guaranteed) to improve performance. This agent compiles a load of information about how to transform the code into a single pipeline, so we’ll call it a ‘compiler’. This then feeds to the next agent that finds missing parts of the program and tries to fill them in with existing implementations. This is more efficient than simply generating new code and more reliable since the existing implementations are better tested. This agent has a knowledge base of existing code organised in grouping that I’ll refer to as ‘libraries’. It creates links in that web of knowledge between the outputs of the first agent and these existing ‘libraries’ and so we’ll call it a ‘linker’.I think it might catch on. VCs: I think we can build this thing for only a couple of hundred million dollars! And the compute requirements are far lower than for existing agentic workflows, so we can sell it as a service and become profitable far sooner than other AI startups. Sign up now for our A round! We have a working proof of concept that can output the Linux kernel, LibreOffice, and many other large codebases from existing prompts!
(DIR) Post #B3Zzaxf1H72of4bYX2 by wolf480pl@mstdn.io
2026-02-22T12:34:22Z
0 likes, 0 repeats
@david_chisnall I wish the market cared about reliability
(DIR) Post #B3ZzzpW8gkAce4JEm0 by hopeless@mas.to
2026-02-22T12:38:52Z
0 likes, 0 repeats
@wolf480pl @david_chisnall > I wish the market cared about reliabilityNobody has cared enough about FOSS maintainers to make sure they can eat. Why would they start caring about the purity ideals of noncontributing users?
(DIR) Post #B3a0Q7MwwFKxXaXuka by wolf480pl@mstdn.io
2026-02-22T12:43:39Z
0 likes, 0 repeats
@hopeless @david_chisnall I don't mean it from a noncontributing FOSS user perspective.Imagine two SaaS companies.One of them takes its time to make reliable software, and run it in a fault-tolerant configuration.The other vibe-codes everything in a fraction of that time and releases a buggy service.Both charge their users a subscription for the use of their service.Which do you think will make more money?
(DIR) Post #B3aFkellxt9OEaPNtQ by ignaloidas@not.acu.lt
2026-02-22T15:35:22.950Z
0 likes, 0 repeats
@wolf480pl@mstdn.io @david_chisnall@infosec.exchange there's no need for reliability when there's a lot of liquidity.(if there was a 1 year minimum holding period on stocks, that would change things a lot, but that would require a whole ton of restructuring of global markets)
(DIR) Post #B3annPfFyjoshGqY88 by hopeless@mas.to
2026-02-22T21:56:51Z
0 likes, 0 repeats
@wolf480pl @david_chisnall Imagine two OSes... OS A "vibe codes everything" and "releases a buggy service" (for decades now).OS B has no AI code, "takes its time to make reliable software" and can be run in a "fault tolerant configuration".So due to your poor choice of example: - OS A is windows, it makes billions. - OS B is Linux, you can share copies for $0 under GPL 2.
(DIR) Post #B3aofyUEj67kKki18C by wolf480pl@mstdn.io
2026-02-22T22:06:44Z
0 likes, 0 repeats
@hopeless So you decided to apply my argument to a situation that is not analogous, to one that compares two OSes whose developers pursue different goals, and somehow you still arrived at the same conclusion as I did.. thanks I guess?Anyway, my point is, @david_chisnall's idea of "technique for reliably vibecoding apps" will not attract the investors he's talking about, because the investors want to make a lot of money, and those paying for software don't seem to appreciate reliability.1/
(DIR) Post #B3apGmjNOg9uaXLKYC by wolf480pl@mstdn.io
2026-02-22T22:13:25Z
0 likes, 0 repeats
@hopeless @david_chisnall A better analogy would be a quickly thrown together system called Unix vs an arguably more carefully designed and higher quality system called Multics.Turns out Multics took too long to develop and didn't get many users, while Unix started later, released first, and spread into many clones (Linux being one of them) and is very widely used to this day."worse is better", unfortunately
(DIR) Post #B3apkwvm2RCGuVWdUm by hopeless@mas.to
2026-02-22T22:18:51Z
0 likes, 0 repeats
@wolf480pl @david_chisnall The OP here is just trolling. There's a lot of fear around AI atm.For future reference although you may feel you laid out your point obviously in the post I replied to, what you actually wrote was a scenario and a question, "who makes more money". It's absent in that text what your position is.I answered your question, if it's agreeing with you then great, we agree on something. Using AI and making sloppy software doesn't seem to stop microsoft making money.
(DIR) Post #B3aqP1UOVeq6dCpMK8 by wolf480pl@mstdn.io
2026-02-22T22:26:06Z
0 likes, 0 repeats
@hopeless I thought my position was clear when I said "I wish market cared about reliability".It implies I believe the market does not care about reliability.I know the OP is joking, but his joke only makes sense if the people and companies that use vibecoding are unhappy that their software is unreliable. Which IMO they're not.
(DIR) Post #B3aryVqLkHdmrXaEfA by hopeless@mas.to
2026-02-22T22:43:41Z
0 likes, 0 repeats
@wolf480pl Yes I can see you thought your position was clear.But your wish about the market caring about reliability was not in the post I replied to. I think you'll find (indeed you just have) a reader can't arrive at understanding your position from that post.Anyway have a nice rest of the evening.
(DIR) Post #B3bQAxbRl5hksFiglc by kdacar@mastodon.social
2026-02-23T04:24:15Z
0 likes, 0 repeats
@ignaloidas @wolf480pl @david_chisnall Lets go back to > 1 second, just as a try...
(DIR) Post #B3bQAygRjzIYE34CCO by ignaloidas@not.acu.lt
2026-02-23T05:06:54.995Z
0 likes, 0 repeats
@kdacar@mastodon.social @wolf480pl@mstdn.io @david_chisnall@infosec.exchange eh, that would only impact high frequency trading, which yes, does suck, but in the end getting rid of that wouldn't change that much in terms of how markets operate at large.FWIW my favorite solution to that side of things would be to move to a double-auction system with a 24h clearing period.
(DIR) Post #B3btZWLZ8A1uFcM4hs by wolf480pl@mstdn.io
2026-02-23T10:36:18Z
0 likes, 0 repeats
@ignaloidas@david_chisnall @kdacar Is HFT a problem tho? AFAIK it mostly does arbitrage trading, which is like, someone has to do it or the price discrepancies will grow...
(DIR) Post #B3buToI1betW7HXWim by ignaloidas@not.acu.lt
2026-02-23T10:46:20.566Z
0 likes, 0 repeats
@wolf480pl@mstdn.io @david_chisnall@infosec.exchange @kdacar@mastodon.social for stock markets where each stock is only traded in one market it doesn't really matter - there HFT is just a drag which mostly works from getting/guessing advance info about other trades (and not like you can't do arbitrage trading on large time periods, if the price updates only once a day you just can't rely on being faster then others to get the profit)and anyways, with a double auction with a decently long period, you get the idealistic view of how the markets "should" work - you get the supply and demand curves, find the intersection, and pay/sell for said price.