HN user
If you have a nearby hackerspace or similar, check it out.
Likely they will be able to help you choose and guide you.
For me the hurdle was less about finding equipment and more being able to learn from experienced people.
There is a part of me that wonders if it's partly just how much they can hold in their head right now, though. Even with the greatest articulation and high density of feeding them, the current setups don't allow them to hold a high-quality, sparse, 'zoomable' model of the world in their head that well yet, which we can do pretty well.
My personal experiments show that giving them tools to access to all past sessions over a codebase helps a lot. When I coded "feature X" 2 months ago i likely specifically mentioned some constraints expressed as abstractions and, if the coding agent checks not only the code/feature it needs to implement/change but also the past sessions over that, it picks them up, and ships code that better fits the overall project.
At least, more than "architectural/design guidelines", since they are more "concrete", to the point for the task at hand.
Sessions self-preserve them for following sessions, which helps, but might also carry over stale things, so some "pruning" helps, and can be automated. Overall, as long as corrections were also made via agents and hence in sessions, they are picked up automatically.
It's not the "human zoom" you refer to, which as humans we can drive/control, but the effect seems to be similar: I read autonomous sessions where it picked up from the past the very design/architecture/abstraction points i would have driven, had I been in the loop.
In team contexts it should not be impossible to share sessions, but I not working in teams right now :D So maybe it's also a "single dev quirk".
Another point is that in a sense, learning to code goes from being told "you are using the_wrong_abstraction/this_abstraction_the_wrong_way/no_abstraction_where_you_should_have", to telling it to others/ourselves.
Since the number of knowable abstractions seems to be "at least one more than I already know", agents can actually be helpful in learning.
After a certain threshold, it basically zeros in a specific domain, but on novel domains agents taught me abstractions, when nudged towards doing that.
Congrats on releasing this.
OTOH all my attempts of driving harnesses via chat have been frustrating because they all fail against the fact that I want to see the code and mobile devices are not really good at that.
Better on tablets, but even there I get more value on having final html artifacts pushed on a server and inspecting them, and dashboards.
Is there some obvious use case I am missing? Or tool for inspecting code?
I don’t run openclaw et al, is that a context where you find this valuable?
separate topic, separate comment
i agree with your point: "we" always wrote code and abandoned it
the claim here is made against flatpak submissions, which involve pr reviews
i think a point being missed is that open source has always written code that was going to be reused by corps, but PRs in it were likely to help humans join open source, and develop coding skills
now they likely just provide RLFH to corps
let's be clear
op doesn't provide code, so my effort stays at throwing in a claude session and providing code without ANY review
trust my numbers as much as you usually trust claude code
trust the original numbers as you usually trust no code
yes unfortunately there is no baseline
once you get past the article reporting, original study lives at https://geopjr.dev/blog/democratizing-abandonware
author provides no repo/code, but describes methodology
i run a 95% autonomous claude code session to re-run the experiment
after all, since he pulls pr/repo data for ai slop, I can just pull all data (not just ai slop) in the same time period and compare
https://github.com/rufasterisco/slopware
1
"ai slop prs/repos" starting numbers mostly match (120 to 199)
i only tested prs from github repos, bringing it down from 119 to 116
still, based on those numbers, looks like we are off by a neat 25%
could be different methodology or claude making mistakes
author mentions doing some manual cleanup
│ │ Original │ Ours │
│ Unique repos │ 120 │ 116 │
│ Maintained │ 32 (27%) │ 58 (50%) │
│ Abandoned │ 88 (73%) │ 58 (50%) │
2 given the above, this is what comparison to "baseline" looks like
as said, "baseline" here means PRs in the same period
│ │ AI Slop │ Baseline │
│ GitHub repos │ 116 │ 332 │
│ deleted / 404 │ 11.2% │ 4.8% │
│ ≥3mo stale (surviving)│ 43.7% │ 39.2% │
│ abandoned (total) │ 50.0% │ 42.2% │ │ alive │ 50.0% │ 57.8% │
post "github fetch" data lives in repo
if you want to run from zero, the repo has the scripts
it will download 600+ MB from github
Thanks :)
As someone belonging to the group you just described, I like discovering things from first principles, and build them. It’s a big part of how I get to learn things, and find it fun.
This thread is helping me see how others addressed the same ideas.
I get and share criticism in the context of “AI hype startup culture”.
But out of it, this thread is really valuable for me mostly because of the links to codebases.
“Siloed individualistic development” openly shared is the part of HN I like most.
The paper’s pip library can be tried here
it's a self enforcing loop
local LLMs builds tool that does exactly what user wants, how it wants it, which is bext UX
this becomes AI literacy
LLMs already nicely bridge the gap form "I want this" to "here's a local page that does it".
examples of tools i have built that requires almost very low tech knowledge * push a button on my phone to take screenshot in my mac (when i watch videos) * help me exercise, gamify it for me * "help me track time spent online to how it impacts what i do in real life, built a tool that rewards and me points me towads things that make me DO things online" * i want to improve my writing, give me exercises and build addiitonal tools (leading to an "append only" digital keyboard i use to exercise )
local AI can already create these tools, and no external company is ever going to beat me/the-user because instead of getting features i don't want, or that almost do what i want, or that do something that advantages the company they just do what I want
Repositories of tools-as-ideas created by others are quite often just index.html and ... that's all? manage data in localstorage, end of it?
Online inferences is still needed for large data (audio/video/images) processing. For now? we don't know, history suggests we'll have the capabilities to do that locally "soon". Or maybe not :)
The main issue is "online for collaboration". Not same user across different devices, that is easy. MeteorJS-style approaches (making local copies of part of dbs, reconcile to remote/origin) seems to be an interesting possibility at small scale, since once you have the right primitives in place you can go horizontally everywhere.
the question of cost to be answered.
Commoditizing complements. If Anthropic/OpenAI/etc is eating your lunch, make it work with cheap local LLMs , you can beat them on price by having local inference you don't pay (nor need data centers for), and try to keep your (user/data) moat.
The more Anth/OAI disrupt, the more likely this is to happen. If they don't disrupt enough (.ie: grow as an ecosystem to defend against incentives to commoditize), then yes, those incentives are removed, but they also leave money on the table, which they need.
Not only at business level, but also geopolitical (to a lesser extent? or not since lots of open weight models comes form China?).
Some things are too important to violate just because 60% of people are afraid.
We need to avoid this becoming "60% of people should be stopped because 40% disagrees with them". Alas, constitutions have the purpose of defending core values. Separation of powers lets judges strike down gov bills and laws.
We have check and balances. Diverging from them as an emergency measure for the "right" reason only makes it exploitable after the next election, if parties swap.
Instead of jumping from project to project, I focus on one (maybe a few) and let myself free while agents spew out their output.
Something physical is excellent for me: minor wood carving, origami, drawing exercises, also light physical exercises.
My trick is to (try to) do something that requires high focus, on unrelated matters.
To give a practical example, the simple gesture to connect 2 points on a sheet of paper via a direct, non trembling line, requires high focus: if you try to do it sloppily it is too long, too short, etc. I need to shadow the moment, gain focus, draw the line.
It keeps my brain in focus, busy and engaged. Videos, podcasts, and in general enything digital seems to distract me away and/or overloads me.
Also, I am back at using pomodoro technique more frequently.
Just some pointers, in case you want to try out, or suggest some you find effective yourself.
Some traits I recognized in many excellent coders i worked with, their drive to optimization, intellectual thirst, critical and creative thinking are attributes i consistently correlated with them being in some sort of neurodivergence spectrum.
Being able to remove the "first step" block is great, but what worries me is that this is coupled with LLMs sycophantic behaviours. My gut feeling is that coupling the feeling of unblocking ones capabilities with dopamine hits with the constant praising over someone abilities is an intro to psychosis and paranoia for them.
I think fundamentally we disagree on 1 principle, that "better" is the enemy of "good". This leads to choosing which tradeoffs to accept. And we are on the same side, to be clear. I want privacy. I also see what you mention, I just frame it differently.
Android being locked down is the worst case scenario: private companies makes rules, an update is pushed, no platform for discourse. It's also the standard business practice when you let companies implement solutions to "privacy problems": put some privacy preserving lipstick on a fredeom restricting measure.... Specifically: we (google et al) need to verify apps so that we don't let them to do bad things to you, like stealing your data and ... sell it in the very same predatory data ecosystem that we have built and that we sustain for profit.
On the other hand, the EU sees that a law has been mocked on the internet since day zero (you must be of legal age to watch porn), in due time (30 years?) this has an impact on society, and shit needs to happen because yes, this is how laws work sometimes: they limit freedoms. They have learnt from GDPR that delegating the implementation of laws to businesses is bad: they defang it and/or twist it so that the concrete result fits business needs rather than the principles established by law (as per above example: gdpr, ads). So, the EU finds its own tech solution, puts down privacy as a core value, ships down a EU wallet and says "this is the reference implementation".
I like this! It's not "perfect", but i prefer this 1000 times over "let Google verify my age".
It seems to me that the EU has done an excellent job: now that society (including actors in bad faith) is saying "we need to protect the kids", we can say yeah ok, here is the good way to do it. They actually thought about this years ago.
Now THIS SPECIFIC document is .... ok!!! Because it is NOT to be read in isolation, but within the context (my framing) of EU actually giving me laws and tools protecting me. Over decades. And I have seen plenty of attempts at breaking those, and plenty of EU votes bouncing back those attemps.
Overall, there are 2 possibilities (aka tradeoffs on better vs good) when freedoms are attacked. One (yours, as a understand it) is to say "this (VPNs, e2e, ...) is outside of the Overton window, just bringing this up is unacceptable/fascist". You have good reason to defend this approach, and it's ALSO thanks to you and other activists (hope this does not mischaracterize you) denouncing and rallying around these issues, shouting "fascists", that we got them revoked.
The other one (mine? maybe?) is to craft a response that exposes the faults at play, naming and shaming business interests trying to hijack age verification to provide them with business advantages (example in this case: internet in Spain "stops working" when there's a La Liga game, etc, I'm sure you know what i'm talking about).
The willingness to rebuke these attacks in debates can be a slippery slope (opening the window). And yet, in present times politicians wear "being shouted 'fascist' at" as a badge of honour and they manage to translate that into votes. There is a correlation that I see between "good" (argumentative discussing to convince) and "better" ("this is just not going to happen and we should not even discuss this because we have no room for fascism here"). Both are valid, going back to the beginnning we disagree on which to employ in this specific case.
All the above is about "framing", meaning a meta-answer over discourse. Also, let me be clear that I am not seeing you, or activists in general, as "mob shouting" by conflating that with lack of critical thinking, or ability to expose that. I have recognized that your position has value, but let me be clear on that :D
Now to tech details.
Locking down network is impossible as long as decentralization is possible. You ban VPNs? People start using TOR. They don't know and care, but in order to watch porn or sports, now they have better privacy protection across many other dimensions. To gain usage, interfaces becomes simpler. VPNs went from being a business tool to being a consumer tool precisely because companies started enforcing arbitrary rules. In order to get there you need to be easy to use, which makes their usage explodes, etc. Constraints, scarcity, or urgent needs drive innovation, so i don not see autoritative pushes vs tech-for-freedom as a zero sum game (probably an even better description of why we disagree?). Since businesses belong to the fabric of society, sometimes business rules goes into laws. And sometimes whatever a government thinks is ok goes down there, principles be damned. And yes occasionaly you get the guy that needs to go to jail, Prometheus-style. Clearly, Zimmermann. Arguably, Snowden. Provocatively, Kim DotCom. So yes, banning VPNs is bad, but isn't it true that we have this problem because everyone can just flip on a VPN at any given moment? Is this not a manifestation of a right that we have "acquired", in some sense?
In this context the EU has done, and is still doing the "good" thing: the EU wallet has not been assigned a budget and shipped over for development to Accenture or Oracle or any other private business. It has been given to open source researchers, and it leverages lessons learnt while building decentralized solutions. While "everyone" was busy scamming users with ICOs, the EU has taken an interest on Zero Knowledge Proofs. And EU bureaucrats have talked to nerds to understand if there is a way to have age verification and preserve privacy and make all the things that me (and you want). Because, EU has been a global pioneer in elevating data protection to constitutional/human-rights status. Data protection worldwide, in the past decades, rests on me and you worrying and "fighting between each others", but mostly on the EU listening to us and being a global pioneer in elevating data privacy to constitutional/human-rights status, via Article 8.
To flip you statement: the outcome of this is not the worst case of a single measure - the outcome in many cases will be the combination of measures taken by most forward looking governments across the globe that each protect certain freedoms.
sorry for the wall of text, i hope it was worth your time
Stopped midway through reading it to clarify something.
I don’t want your conversations :)
Anthropic has it and this is beyond me. My plugin commits to your repo. When it comes to keeping the WTF DUDE out of conversations, LFS gives you a net trick. You can edit LFS blobs independently from git repo (different storage), so up to some point you can independently edit them out without touching git history (with caveats, it’s a rabbit hole).
Also, I think the inflection point is making it public. Git helps, just “fork” the repo without LFS to publish code only, or with a “sanitized” LFS (it just needs a touch of tooling to play with it).
I am also shipping a hook that sanitizes secrets by default (because security) and can be used also for keeping parts of the conversations… “tidy”. I have built the “cleanup swearing feature”. Yes sorry it’s llm-turtles all the way down if you want automated, and extra cruft. But is also ok?!? I have a concern, I want to address it, I need to put some extra work…
I just want to clarify that privacy is my concern too and I have found that it’s not impossible.
I did not started coding until I found out that there is a way to contribute to a repo without participating in the “sharing conversations” game. (Not difficult: it’s your machine)
I am not publishing the repo until I have had enough conversations like this to introduce different opinions in my line of thought, especially around non technical hurdles.
My biggest concern is “why the hell would I teach an LLM that much of me, knowing very well this is how I will automate myself away”. But even then, it’s either anthropic doing it, or me (coder, not plugin owner) AND anthropic doing it.
I am not advocating to giving away my skills for free. One feasible variation of this whole record conversation is “commit code to company repo, commit reasoning to MY lfs”. Why not? It’s my critical reasoning!!!
Thank you for clearly stating that democracy is not a value for you, instead of dancing around the concept with semantics.
I completely disagree with you, but at least we clearly know why.
It has been chosen as a chapter title.
In my view, it lends more authority to that statement over the other citations in that chapter.
I am inclined to take this as a honest editorial mistake: adding a ? at the end would have been the right choice.
I might be a bit lost on what you/we mean by context. For me, it’s the original pdf from the EU, no quotes.
https://www.europarl.europa.eu/RegData/etudes/ATAG/2026/7826...
Preserving privacy within a rule based democracy is important to me.
This is the foundational tool for 450 million EU citizens, so I think is very important.
We likely have different interests.
Ok, my answer was sloppy. Here’s what I meant:
1. Context is “EU digital identity”. For a decade EU asked researcher how to have a way to verify age only, without extra data leaking. They have a working solution, and it’s the one rolling out to EU citizens.
2. This document talks about VPNs because they have been bought up recently as “how to skip age verification tools”. It is a legitimate concern. Every EU citizen has/will-have a privacy safe wallet to prove age, users from other nations will not, EU minors can just VPN to nation X, and skip age verification.
3. The org producing this doc outlines that yeah, the above is true. It’s actually a balanced doc. Each of us would have written a different one, sure. I likely would have liked “yours” better, since I think we feel we share common values. I’m just saying i don’t thing it is misrepresenting reality. The doc targets eu legislators, likely not tech savvy.
This is not about restricting access to VPNs, this is about outlining that they exists, that they have an impact on solutions proposed for age-verification. Did it not exists, it would reinforce that eu votes on shot without having any grasp on what is at stake.
I actually agree with you: I see civic liberties under attack way too often (and try to contribute as much as possible to upholding them).
But by large, the EU has done a good job at upholding those freedoms. Repeated attacks on those freedoms have been rejected when it was time to vote (in the EU parliament!!!). This makes me confident in the process.
Yes, of course, we can always have “better”, but at some point calling out as fascists some legislators trying to understand what’s the relationship between VPNs and age verification seems to me as the opposite of wanting them to be better educated.
To precisely answer the “restrict access to VPNs”, no of course that’s not “good”. But I like the fact that EU legislator get to read that document, instead/on-top of some partisan mumbo jumbo from whatever news outlet.
I am sorry you see it this way, when the very subject at hand is a practical example of how the EU has planned and built a wallet around the very same ideas you seem to cherish.
Unfortunately, now that it comes to the news cycle, it’s easy to get outraged around misleading headlines.
I encourage you to invest time in researching what the EU has done in the past decade around digital identities and their framing around privacy questions on this. I hope you will find, as I do, that it moved the needle in t he right direction.
From a tech perspective it has been a solved problem since about a decade ago, via DID (decentralised identities) and their Verifiable Proofs.
The EU digital wallet framework is built around those, and your suggested scenario is a first class citizen.
It is now moving from the academic/research world, to the political field, and feedback/pressure from both commercial groups and political agendas is muddling the field.
Here are some links to canonical docs, you can easily find high quality videos that explain this is shorter/simpler terms to get a grasp of it.
https://www.w3.org/TR/did-1.0/
https://www.w3.org/TR/vc-data-model-2.0/
A note: it’s one of the healthy byproducts of the blockchain age, don’t get sidetracked by some hyped videos from crypto bros.
The title is also the exact title for that paper’s chapter.
You are right at pointing out that the paper is overall presenting the subject in a balanced manner, unfortunately it seems a bad choice was made when it came to that specific sentence, that gives a venue for it to be fed in the outrage machine.
https://www.europarl.europa.eu/RegData/etudes/ATAG/2026/7826...
EU enshrined privacy in its charter of fundamental rights. GDPR was and still is a major protection.
US, from its biggest companies to the whole of Silicon Valley culture has done the exact opposite.
Within the EU, multiple attempts at pushing changes in opposition to this have been proposed, debated, voted on (and rejected), as democracies do.
Not perfect, but when you come down to laws, EU bureaucrats gave EU citizens article 8, US gave them the CLOUD act.
"AI speedtracks bullshit shops into bullshit factories" is the other side of "AI enables efficiency gains beyond immagination". As a freelancer I get to see both in action.
No surprise! Do you rememeber agile? Sometimes it was pragmatically applied towards efficiency, sometimes it became a bullshit religion full of priest and ceremonies. And on i could go, with more examples, the gist stays the same : new tools, speed increase, faster crash or faster travel depends on the trajectory the company/team/project/thing was already on.
A special note on "People who cannot write code are building software." "Fuck yeah" to that! Devs has shipped bad software to people in other departements/domains, for ages. They would never build something better if what they had was good in the first place.
When we (coders/startups) were doing it it was "innovation", now is "elephants in the china shop"? And this is not a rethorical snappy question: that IS innovation, instead of critizing the "wrong schema" ... understand the idea, help build it and do the job: ship code that works and is safe.
Also, grey-beard here, pls, don't think you can ever have a stable job especially when code is around. It keeps changing, it always has, it always will. AI bringing unprecedented changes is hype. The world always changed fast.
If "you" picked software development because of salary, you are in danger. If you did it because you love it, then tell me with a straight face this is not one of the best moments to be alive.
Let’s see if someone can point me towards some resources over the following.
The problem is mixing vibe-coding and agentic-eng, and switching the brain in 2 different modes (fast-feedback gratification vs deep-focus gratification).
There’s no clear cut rule on what works. Different people, different brains, and especially amongst devs some optimized low-key neurodivergence.
And then there’s waiting mode, those N seconds/minutes that agents take to think and write.
What’s the right mix? Keep a main focused project and … what do you do in the meantime? Vibe code something else? Hn? Social media? Draw lines on a paper sheet? Wood carving? Exercise? Rewatch some old tv series?
I have experimented….
There are side activities that help you go back to the task at hand in the correct mental framework for it. Not just for productivity, but for efficiency and enhancing critical thinking on the main task. Or whatever you choose to optimize for. Can anyone point me towards some people talking about this?
Exactly. As long as the codebase is consistently following some given patterns, LLMs nowadays stick to it.
Understanding that limiting number of “design patterns” in a codebase made it better (easier to code and understand) was a good proxy for seniority before LLMs.
Now it’s even better: if all of a sudden “unusual code” is in a PR, either the person opening the PR or the one reviewing it has lost touch with the codebase. Very important signal, since you don’t want that to happen with code you care about.
I like this chat, if you want we can continue this privately (username Gmail).
You are bringing up valid points, and we have scars from the same battles.
Given all this, what is bad about preserving the conversation that led to the code creation?
It might be wasteful, sure, if it never gets used. It might be bad, if it’s misused. But in the right hands (or with the right tools) it holds value.
Presently, we might not have them (agree to disagree to same degree), but given enough time will we not regret not having stored it, if better tools emerge?
There are many more angles. .ie: you mention damage to critical thinking. And I agree about it. Yet some conversations are better than others on this aspect. The conversation doesn’t magically make you develop spidey senses, but if I had to learn a new project/skill, wouldn’t a selection of conversations + code be better training material than code alone?
I tried to stay light so some terms are overloaded and some concepts oversimplified.
Yes, it’s the new normal. That’s the issue that worries me, not to which specific war/faction this applies.
Going from “Metadata fusion for targeting advertising” to “same, but for killing”, mark to me the moment where an industry is complicit.
It is why we updated our mission, and why reliability is woven throughout our new credos.
… later …
Over our ten years in existence, we have come across many of these cosplayers before, and every time we have put in the hard work to out-execute them and provide superior results.
… finally …
We have spent ten years doing it the hard way - from making models better to turning them into applications that work when it actually matters. I’m extremely proud of the work we are doing and the mission we are on.
What happened to the mission here? Did it get updated? What was it before? What is it now?
If this was to inspire confidence, it did not really work for me. It made me feel like a shell game was being played.
Also, not a hint of how they provide reliability.
Who is the target for this message?
let to unwrap, let me try to do it
i misunderstood "wall of text" (i was thinking about bloating repo with it), my solution to understanding is just to create ad-hoc tools to parse the json
i coded a web ui with simple toggles: show me what user said, what llm said (nice to see what I was thinking about, nice to see how LLM came up with solution X, you get tools calls, maybe it found something i didn't think about or viceversa) you can search/grep (.ie: did i consider idempotency when i build feature X? open session, search/grep idempotency) you can, up to some point, resume the conversation (yes i know, cache busting makes some usages of this impractical, but in general resuming and asking "when we did this, did we think about that" tends to work... let's say that research is ok, time travel, meh)
overall, one of the advantages of LLMs is to be able to direct then ad data for insights, via standard CLI tools, via specific prompts, or building some mini tools (yeah vibe coding is fine sometimes) whatever my question, if i have data i can have an answer
LFS helps with the second aspect (buried bullshit). Unless you smudge, you have a pointer, and that is just 3 lines. You need to learn some ergonomics, but ok, some of us learnt how to use Jira XD
Taking your position a bit further, yes, committing chat sessions implies that you also need to review them so that bullshit doesn't filter through. Milage varies based on your personal preferences, which project you are working on, and many more heuristics. Some will find it boring, some will think it's good project maintenance, all should be able to find a way to handle this based on their preference.
It is also nice to pointout that cleaning bullshit doesn't need to happen at merge. LFS blobs being stored separately, you can have side flows helping you out, without clogging yoou CI pipelines.
"no dude"-> rules you can put down SOME rules usually this happens to me at PR. I am tired fo saying "you should always check X", so i bolt it down "someplace". I am running the usual motions i suppose most of us try to adopt: put this down in agents.md, in folder x or y, in path-scoped rules using agents, in memory files (i am exporting/importing those too), in subagents that review code before PRs.
in the end it's an unsolved problem at large, but 1. hopefully it will get better, my feeling is that it's just a cambrian explosion, and the fittest will survive... (also, owning the harness should help, i suppose .. i use claude code :D ) 2. in a team, having personal styles surface is valuable. "dude don't do that" is quite often .... design. When rules go in the repo, at least we can find an agreement in person, and at PR is not about linking a document you read at onboarding, but finding out why the agent did not respect the rule. To me, that is more grounded in a tool. 3. rules are ... not static? We change our minds? We get better at things? We want to experiment? I am not advocating for a perfect rule system that replaces me, but for a good enough one that removes cruft from my daily job.
I think my approach is actually helpful when it's time to find root causes (YMMV). Via tools that parse sessions, you can see when that specific portion of code has been written with a better granularity. During that bit of the conversation the user was worried about X and asked AI to do Z and AI read this and that file and "thought" this and that and wrote that piece of code. Maybe the user was making wrong assumptions, maybe the LLM did not read the correct files or instructions, in any case you have a better tool for investigation. It's up you to decide wether to use it, wether this lead to just solving the bug or also fixing instructions, etc, i am just saying that it actually helps to have some measure of the context on which this change made sense.
"Fluffy wall of text that looks good but is factually wrong. "
it might be good or bad, right or wrong, but what is in the sessions is the truth of what happened. PR desc are horrible, i share that feeling with you, but having the story of how that thing happened is just not the same as "final summary of what we did in the past X hours".
As a sideline: LFS doesn't really pollute your repo once you get to learn its ergonomics. Having chats in LFS also lets you approach this
Reproducibility... To me those conversation are basically the history for decisions taken while implementing. They are documentation. The real problem with docs was that no-one has ever liked writing them, nor it was easy to implement a standardization around them. If you just record/log, there';s no extra effort needed, and once there tools and LLMS are pretty good at helping us extract insights.
I am also assuming, there is a correlation between quality in the conversation and in the code. I know, i'm being hand-wavey, but overall i think critical thinking is what makes code better, and being able to see if/which it has been applied can be a good proxy. I ask for forgivness already: I not going down the rabbit hole of quantifying quality etc. It's a broad statement that should be taken with a grain of salt.
If you want to go abstract, you can think of coding as going from thoughts to 0-1 in bits. We have high(er) level languages that help us organize thoughts to help us so that we can better keep them in our cognitive flow/load. LLMs are an upper layer, that scrambles the code and make it more difficult to grasp. But the reasoning behind the code is now available, and quite easy to parse. I think this is the core point to me. Code is an intermediate artifact between thinking and bits. Now we have a second artifact: the conversation/decision that led to that code. Why are we not storing it?
disclaimer: I am, of course, mildly in love with my own project and ideas, so possibly i like this too much just because i built it. IKEA effect or whatever.