armcat

> Pando now powers all development in OpenAI’s monorepo.

Monorepo. I keep hearing from various folks across the more frontier tech companies, that they have switched to a monorepo to improve agent-scale dev performance. Anyone have similar findings?

I spent 10 years working with radio access networks (RAN), first in WCDMA (3G) then LTE (4G), then 5G. Our systems were also software defined radio (SDR), but, and this is crucial (and the paper points to this), the SDR as "malleable" as it is, is still highly dependent on the underlying hardware to achieve good performance.

Also, we spent huge amount of time making sure uplink performance is top-notch, as is the general stability and determinism, i.e. jitter and tail latency. In the paper they show that OAI is quite unstable, and they only achieve 5-49% of theoretical uplink capacity.

Also note this is a tiny setup, single server, four simultaneous UEs (phones). The systems I worked with handled 20 000 phones per second, with quality guarantees, in environments like central Tokyo and midtown Manhattan.

So great for independent research, but unfortunately, still very much bound to small end research.

> the findings are not “a demonstration of a new antiaging treatment for people,”

Regardless, every other study shows only positives of lifting and regular exercise, so just do it!

I haven’t looked into the site code so don’t know if it’s some tracker or pure coincidence, but I own 15 of the first 20 books that showed up!

Game of Thrones author George RR Martin writes all his novels on an old MS-DOS machine, not connected to the internet, and he uses WordStar 4.0. [1]

[1] https://www.bbc.com/news/technology-27407502

I hiked Norwegian fjords above Bergen a couple of times in the past, highly recommend it if you ever get a chance.

Also: Norway has one of the largest sovereign wealth funds in the world, valued at $2.2 trillion; over 50% are investments in US assets; close to $200 billion in US Treasury securities; and is a major shareholder in US corporations, especially across the tech sector.

So well done Norway, this is how you deal with clowns, not debate or argue on social media, but rub their face in your pure awesomness.

I actually still write my own blog [1] :sweat_smile:

Pure html by hand, using vim. No frameworks, no nothing, single stylesheet. I think there are a few others around here that still do this.

[1] https://armincat.com/

I absolutely hate AI writing as well, but I suspect since the author is French, and the underlying code in their GitHub project [1] uses a lot of French naming, that it was more of a translation aid.

[1] https://github.com/Zebra-Rodeo/marelleo

First off - well done, this is amazing. Secondly, it's a fascinating read how you basically figured it out, one mistake at a time, like not connecting or fastening the battery correctly. This is the way! We make mistakes and figure things out in our journey to make something interesting, and learn along the way.

This opens up so many interesting opportunities. In principle one could compile a small VM inside the LLM weights. The VM can host for example a Python interpreter, a shell and tools like sed, cat, grep etc. Instead of LLMs having to do slow autoregressive token emission with the current "external" tool calling, it could literally execute everything except web search, inside the LLM, with just matmul operations. You could probably optimise this so it runs in batches. You could have a gdb like application that can step through the LLM forward pass. Anyway, just a crazy thought. Have a great weekend everyone!

The article doesn't establish whether AI ultimately benefits attackers more than defenders. Open weight models give defenders access to the same capabilities. At the very least the community has a level of symmetry they wouldn't otherwise have.

His team is doing amazing work in making open weight models even better. Chinese models are notorious for their thinking verbosity and tenacity to call tools repeatedly [1] so his team is making them more efficient and on-point [2].

[1] https://armincat.com/articles/ai-agent-executed-same-query-2...

[2] https://bottlecapai.com/post/thinkingcap-qwen3-8-flash-next/

There is a human/user element here as well - will the users check the citations, if they are provided inline? I recall in the early ChatGPT web search and Perplexity days, most of the citations didn't work (made up, or 404). You get a false sense of security by having a "[1]" next to the stat or a claim. Maybe labs companies should have some additional quality ranking/checks on these, if it's in their interest of course.

I know it was tested in some "trial classrooms" and the response was very positive but I've left that company since and don't know the status. It was part of a UN programme as well.

But essentially it's absolutely possible to have a little cigarette box thing with most of the worlds knowledge at your fingertips, completely offline, and it doesnt require LLMs but just traditional information retrieval techniques.

I worked in legal tech/AI. It's relatively easy to reach the capabilities of Legora and Harvey. My finding is that it's the industry itself that's very tricky and old fashioned. Lot of legal contracts at the large law firms (which Legora/Harvey are targeting) are controlled by iManage and NetDocuments systems. To integrate into their workflows you have to be "chosen" as a development partner. The said law firms also care very deeply about security and audit trails, where the documents reside, how they are processed, etc - at least on the surface. Despite their size and wealth they have invested very little in their in-house data & IT capabilities - maybe they have couple of techies working full time, but mostly they outsource to other companies. They also still print documents and do manual redline. And on top of that you have this insane GTM from Legora/Harvey where their sales peeps are crazy good, and work insane hours.

So it's not really a technical challenge, it's more of an industry challenge, so they will happily buy Legora/Harvey licenses. But maybe (probably) this will change over time.

Median of less than 2 seconds for final word after its spoken on esp32 is insane, amazing work!

I've been using this one for a while: https://github.com/K-Dense-AI/scientific-agent-skills

It's quite impressive especially if you want to run some econometrics or proper statistical analysis. Currently it has 55K stars on GitHub (compare to 3.5K for the MS one).

I asked ChatGPT and it answered Joe Biden. I used Google Search with Gemini summaries and got the same answer.

Regarding Google is it geo dependent? Like Lake Ontario?

Graphs are fantastic - PageRank [1] that powered Google Search (still does to some extent), TextRank for extractive text summarisation [2], Louvain for neighbourhood detection [3] all use graphs, as well as tonnes of others like belief propagation, Markov clustering, A*, and so on. So yeah, learn it.

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

[2] https://aclanthology.org/W04-3252.pdf

[3] https://en.wikipedia.org/wiki/Louvain_method

Back in 2018 I was working on a project for educating schools in certain parts of Africa and Middle East, on AI. The issue was it had to be air-gapped (no internet guarantees) and small/portable. I ended up downloading Wikipedia (not all of it), and then created a lightweight inverted index (for search) and TextRank (for summaries). The whole thing was on a Raspberry Pi, and installed in a small plastic enclosure. We had many of these and could easily ship them. There was an "AI Learning Module" as well we built, that started with Scratch, and then moved into Python. But if I was to do it all over today, I would probably add a tiny LLM and maybe a small ASR and a TTS model too, and you basically have a completely self-contained AI knowledge assistant in a cigarette box. The point being, you basically also have a "survival AI" you can take with you. Of course you still need electricity...