Hacker Newsnew | past | comments | ask | show | jobs | submit | cookiengineer's commentslogin

Shameless drop: My own agentic environment is also using a summarizer to sum up agent histories when they overflow in their context windows. Additionally, all short lived agents are based on requirements (WIP) as a centralized point for code, unit tests, and architecture.

(Everything is tailored to Go as a language)

Works pretty good so far, the user only interacts with the planner. I'm working atm on the requirements to have a spec driven workflow. Web UI is the most polished atm because of ability to have agent tabs on the side for better overview.

In case anyone is interested in this attempt:

[1] https://github.com/cookiengineer/exocomp


...because Alzheimer is a dormant side effect of a virus, not of a messenger chemical. But that doesn't go well in studies and "self populism" of what funded research wanted to hear.

If you study effects and not causes due to lack of measurements for reproducibility in any field of research, that's what comes out.

Also check out how the new and promising correlation started by observing the Wales eligibility for mandatory shingles vaccination during an outbreak and the effect on that test group when it comes to alzheimer or dementia in their old age.

Note that shingles (herpes zoster) virus is a dormant virus for decades, and it's not really treated because of that.

Also note that this was only discovered because people died and their data set was publicized because of that, which I hope that can happen in an anonymous way due to it being invaluable for medical research.

[1] https://www.alzheimer-europe.org/news/analysis-electronic-he...

[2] https://pmc.ncbi.nlm.nih.gov/articles/PMC11485228/

[3] https://www.sciencedirect.com/science/article/pii/S009286742...

[4] https://www.alzforum.org/news/research-news/shingles-vaccine...


Gee, that sure is a confident statement of fact.

Or maybe virus activity is one way that a negative feedback loop involving protein aggregates can begin...


“Complications due to unaddressed microbial infection” will read as pretty confident, too,

but it’s still pretty vague once you’ve really dug in.


That's why I was emphasizing "one way" and "can begin".

Clearly viral infection may be a distal factor but it is not the proximate cause of Alzheimer's... which is quite conclusively due to protein aggregates.


I don’t find any of it conclusive.

Protein aggregates seem like the effect, with many causes.


Yes, exactly. Whether it APOE mutation, traumatic injury, metabolic dysfunction, Herpes infection, or some other inflammation that upregulates kinases, you end up with hyperphosphorylated tau which in turn forms the neurofibrillary tangles that destroy nutrient transport in neurons and eventually kills them.

"Neuron death by protein aggregates" is the best way to define Alzheimer's. Anything more specific refers to only one of those aforementioned causes; anything less is just "brain don't work no more."

These clickbait headlines are so frustrating, especially since the article itself explains the tau mechanism and all the progress that has been made in understanding the disease.


Sure is a line of inquiry worth pursuing either way, no?

It very much has been. Which is why it's tiring to see these articles (and HN comments) portraying it otherwise. Search HN for Alzheimer's and you will find lots of updates on the research and lots of the same uninformed comment threads.

Not always. Genetic causes are known.

... which kind of points to the indicator that "Alzheimer != Alzheimer", implying that too many diseases with the same side effects are categorized together?

A lot of virological and parasitical components have historically been wrongly associated with genetic markers, too. Toxoplasmosis parasite comes to mind.

[1] https://en.wikipedia.org/wiki/Toxoplasmosis

[2] https://en.wikipedia.org/wiki/Toxoplasma_gondii


Non-sequitur

> Non-sequitur

Not sure what you are trying to achieve with comments like this, besides intentional gas lighting.

Could've commented with links to scientific articles or papers that disprove my theory.

Instead you chose to be ... this?



You do realize that they are referring to the same study and dataset, which showed that shingles is correlated to APOE4, right?

Not sure if you are trolling at this point.


I am not a researcher in this field. I have read a lot about APOE4, and nearly everything I have seen about APOE4 makes it out to be the clearest of all predictors for Alzheimer's. I get that you're upset that I posted like I did, but I am not trolling. The point was that genetic causes are not an exceptional predictor for Alzheimer's. I had a hard time seeing how the best established predictor for Alzheimer's validates there being too many things labeled as Alzheimer's. If I had posted with a focus on some edge case, then it probably would have made more sense to me, but as I read it, it really seemed like a stretch.

Dropping this thread now. I am fine with being wrong, but my brief posting was not trolling.


Non-diagnostician

Point stands.

So does the lack of a model for Alzheimer’s,

and other chronic illnesses,

that the consumer-facing medical industry prefers to dismiss.


The tau hypothesis is looking like a good model.

I didn't argue a model beyond one cause.

In my opinion current research should focus on revisiting older concepts to figure out if they can be applied to transformers.

Transformers are superior "database" encodings as the hype about LLMs points out, but there have been promising ML models that were focusing on memory parts for their niche use cases, which could be promising concepts if we could make them work with attention matrixes and/or use the frequency projection idea on their neuron weights.

The way RNNs evolved to LSTMs, GRUs, and eventually DNCs was pretty interesting to me. In my own implementations and use cases I wasn't able to reproduce Deepmind's claims in the DNC memory related parts. Back at the time the "seeking heads" idea of attention matrixes wasn't there yet, maybe there's a way to build better read/write/access/etc gates now.

[1] a fairly good implementation I found: https://github.com/joergfranke/ADNC


> I'd be genuinely curious what you could switch to that still has MV2 because, AFAIK, Firefox is the last holdout.

My last hope is ladybird right now, I don't use Firefox or Chrome as my main browsers anymore, and use them only within temporary sandboxes. Without history, without cookies, without logins for the most part.


You use ladybird as your primary web browser? And it works?

For the most part, it doesn't. It's not a consumer ready browser, but a pretty nice little rendering engine. If you use ladybird as bindings, it's a bit unstable right now because they are refactoring a lot of parts in the codebase.

I built my own tools on top of it, mostly to use internet websites and selfhosted kiwix archives with my local agentic env.

I guess what I am saying is that I don't have a primary browser anymore. Not a browser where I just can trust it that it doesn't do shit with my data. Being able to selfhost kiwix is a superb internet experience if you build your own search dashboard for it, I can fully recommend it.

Have to merge my things upstream with ZIMdex when I have the time (probably around June).

[1] WIP https://github.com/cookiengineer/exocomp

[2] WIP https://github.com/cookiengineer/zimdex


It seems to me that --unless you really, strictly compartimentalize your browser usage--, using multiple browsers will only supply your data to more parties.

Ladybird supports MV2? I had no idea they have extensions.

Ladybird is many years away from being usable by a casual human. The hope is it turns out to be a great browser eventually.

[flagged]


> Good luck with the main developer being in the alt right.

Sources? I can't find anything on that via google/ddg (Germany)

edit: oof.

[1] https://drewdevault.com/blog/Cloudflare-and-fascists/


Linking a pedo-leftist schizophrenic's blog post as "proof" does the complete opposite of supporting the claim.

> Linking a pedo-leftist schizophrenic's blog post as "proof" does the complete opposite of supporting the claim.

Sources for those pretty serious claims?



Oof indeed. Now I know that Kling is indeed open towards some alt right positions, but I really wouldn't call him a fascist for that. Conservative probably, but conflating conservative positions with fascism is probably not helpful in the fight against the real fascists.

But also oof to .. some other items there from the blog. Apparently rsync is now banned from the list of acceptable software, because they do not ban LLM's completely?

https://drewdevault.com/blog/rsync-without-rsync/

Sounds like you will never run out of problems, with a ideology like this.


Isn't this blog post more evidence that drewdevault became an extreme leftist?

I mean he's basically going off a checklist of leftist stereotypes here and trying to check as many of them as possible.

Meanwhile the other guy he's criticising is literally just a standard right-wing conservative, not far right, not alt right, just the regular kind. The far right I've seen is basically beyond the idea of being merely anti-immigration, they demand ICE style mass deportations immediately and in every country.

If both of them met in a bar through sheer coincidence, I'd expect drewdevault to start the fight.


Sorry, but painting these people as "standard right-wing" is just evidence for the shifting of the Overton window further to the right. White replacement theory and expressing support for an alt-right ideologue who manipulated people with bad faith, dishonest and downright monstrous arguments is not "standard right-wing".

Charlie Kirk was for mass deportation. He didn't even hide it. He said it openly. How do you come off saying that these people aren't far-right or alt-right when they are unabashedly so?


Well, the overtone window certainly changed, but ... I judge a bit different here.

"expressing support for an alt-right ideologue"

This is what Kling actually said:

"RIP Charlie Kirk

I hope many more debate nerds carry on his quest to engage young people with words, not fists."

I also support fighting with words, not fists. I do not support his ideology at all and would have loved to debate him openly, but the concept of murdering someone for having the wrong opinion is disturbing to me, so I agree with Kling here.

And about "white replacement"

"'White males are actively discriminated against in tech.

It’s an open secret of Silicon Valley.'

One of the last meetings I attended before leaving Apple (in 2017) was management asking us to “keep the corporate diversity targets in mind” when interviewing potential new hires.

The phrasing was careful, but the implication was pretty clear.

I knew in my heart this wasn’t wholesome, but I was too scared to rock the boat at the time."

He said whites were discriminated for being white. Not replaced. That is not really the same to me.


>White replacement theory and expressing support for an alt-right ideologue who manipulated people with bad faith, dishonest and downright monstrous arguments is not "standard right-wing".

It is now. That's what the shifting of the Overton Window and normalization of right-wing ideology does. These aren't fringe beliefs anymore, they're commonly held, mainstream right-wing views. They're policy within the US government. Charlie Kirk was treated as a martyr and a hero by the administration. He was treated with more dignity and respect than war veterans. The DHS posts memes about mass deportation.

The "far right" and "alt-right" no longer exist. Those labels are no longer useful and no longer describe reality.


Aren't fascists the ones that want you to correct your language?

Came here to reply with ImHex.

It really is by far the best hex editor I ever used, and sooo good for reversing arbitrary binary blobs where you learn incrementally more about its structure while reversing it. The imhex patterns repo [1] also contains so many formats, it makes binwalk almost useless in comparison.

[1] https://github.com/WerWolv/ImHex-Patterns


To me the best "tradeoff" right now is buying used Fairphones from ebay.

It is LineageOS HEAD compatible and has replaceable batteries.

But it has some quirks. Medium performance if even that, non working fingerprint sensor. Camera quality from 2005.

I don't have gapps installed so I'm using my phone without any type of payment/2fa/banking apps. That decision from opsec makes it easily reflashable, so my anti malware strategy is essentially just reflashing the phone every couple weeks :D

My battery usually lasts a week because of using only f-droids chat, navigation, and translation apps for the most part, aside from the browser. I use Firefox with uBlock Origin, saves an insane amount of battery lifetime.

To me, repairability is the feature I value the most in a phone, so I'm kinda willing to compromise on the other features.

Fun fact: Did you know that WhatsApp, Telegram, and Signal all restart themselves when you connect to your headphones? If you froze them before, they'll just drain your battery again when you have any bluetooth changes. You can easily verify that by staying in airplane mode and freezing them, then connecting your headphones in airplane mode.


> LibreOffice Calc

Mentioning libreoffice as competitor to Excel and Access is like you haven't understood the market, at all.

Excel is a cross department business automation database, which can sync/pull/push datasets across filesystems and networks.

VBA is the single most used language in Enterprise because it allows to automate pretty much any financial workflow. And more importantly: automated by non-programmers.

Libreoffice is made for private users, and that's not the same users that VBA powered office documents have.


are you trying to say that i cant use libre, to automate, share, or collaborate datasets across a network?

https://help.libreoffice.org/latest/lo/text/sbasic/shared/vb...

are you trying to say its too hard to step into libre from VBS?

https://libreoffice-basic-reference.readthedocs.io/en/latest...

you can stay with MS if you want, but really you dont have to.

also i didnt mention libre as competitor, but as replacement.


You can do all those things. But as someone who used VBA extensively and often got hired because of my automation skills, not having VBA and other aspects of excel would be a non-starter.

your sure?

its really not that hard, and it might be useful, if MS ends up finding that final straw that breaks it for everyone, you would be better off having a head start and level ground, rather than staring up a wall for employment.

i recommend you orient to it, for future proofing.

scripting:

https://help.libreoffice.org/latest/en-US/text/shared/guide/...

API:

https://api.libreoffice.org/docs/idl/ref/annotated.html

BASIC:

https://wiki.documentfoundation.org/Documentation/BASIC_Guid...

Working with VBA Macros

https://help.libreoffice.org/latest/lo/text/sbasic/shared/vb...


It's not a question about implementability.

It's a question about compatibility.

As long as xlsx files have to be modified, libre office is a non replacement.

No business would even dare to risk this from an operational perspective. That's my whole point, and the whole argument why Microsoft created their own "dip" with it.

If you as an open source promoter within the company tell C-staff that "you found a solution that might be compatible" they gonna ask you what exactly needs what amount of time. And believe me when I tell you, even getting a sharepoint workflow to run with libreoffice is almost impossible without replacing pretty much everything underneath it.

Making MS office as uninteroperable as possible is the reason companies cannot switch, because they have a legal requirement to archive and access the document for at least 10 years (in some industries up to 20 years when it comes to book keeping and accounting).

So if you propose libreoffice as a solution that

- isn't compatible 1:1

- isn't even guessable how long it takes

- forces unpredictable infrastructure changes

- ends up not rendering your documents that are _legally mandated_

Then guess what the response of your CEO will be.

No amount of downvotes or "opinions" on what is better will change this.

I'm a proponent of open source, but leadership of libreoffice does not seem to understand _why_ companies are using Microsoft office. And that is the core problem that has to be fixed.

There needs to be a predictable and guaranteeable migration path. And as long as there isn't even a converter wizard or anything that helps you with that, libreoffice is a non starter.


its all too hard, seems to be the source of friction.

The French government decided on Grist as their replacement. It looks pretty promising: https://www.getgrist.com/

Where you see a problem, I see an opportunity.

The obvious solution is an AI consumer, duuuuh!

The dollar must flow. The dollar is life.


Thou shalt maximize paperclips

The best game ever written, apart from 3D Monster Maze on the ZX81 and Elite on the BBC Micro.

> libcrypto no longer cleans up globally allocated data via atexit().

> OPENSSL_cleanup() now runs in a global destructor, or not at all by default.

Oh oh. Heartbleed 2.0 incoming.

I really do hope that they broke APIs specifically throwing errors or race conditions so that devs are forced to cleanup. Otherwise this is going to be a nightmare to find out in terms of maintenance and audits.

I mean it's a new major release so it's a valid design change. But I hope they're thinking of providing and migration/update guide or a checklist to reduce usage errata.

(I'm heavily in favor of deprecating the fixed version method names)


The fun part is that Google Safebrowsing doesn't even flag the malicious company's website.

And on their pricing page they offer all plugins as a bundle for 0 USD per year! What a steal! /s

Don't click on this, I would assume it may contain malware: https://essentialplugin[.]com/pricing/


Consider applying for YC's Summer 2026 batch! Applications are open till May 4

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: