Dominik Kowalski

👨‍💻

[Dominik Kowalski @doko_dev]

@SlawomirMentzen

[Dominik Kowalski @doko_dev]

@adamSzlapka @donaldtusk tobie sie często prawda z fałszem myli

[Dominik Kowalski @doko_dev]

@Lukasz_Bonzel @OficjalneZero xD

[Dominik Kowalski @doko_dev]

@NathanFlurry @AmpCode @rivet_dev 😲 didn't know that wow

[Nathan Flurry 🔩 @NathanFlurry]

Helping scale @AmpCode on @rivet_dev has been such a pleasure this year!

Getting to see how their team works on Amp and how they use Rivet Actors to build the future of coding is a glimpse at the next decade of engineering will look like

[Dominik Kowalski @doko_dev]

😲

[Rikiya Takehi @rikiyatakehi]

We asked GPT-6 Astra to edit Qwen3.5-0.8B weights to improve math.
It directly changed only 0.016% of weights, fixing 0.8B's reasoning loops & improving math up to 6x and even instruction following 3x, without gradients or training.

We call this Weight-Space Programming: frontier LLMs can now natively read/write neural network weights! 🧵
Blog: https://t.co/bOWCcFhCVq

[Dominik Kowalski @doko_dev]

@PatrykLDev can't wait! are there any plans for TUI so we can use it with herdr/moshi?

[Dominik Kowalski @doko_dev]

@krakow_pl do kosza z tym

[Łukasz Bok @LukaszBok]

Ataki tego typu na większą lub mniejszą skalę zgłaszają też Holandia, Irlandia, Estonia, Luksemburg i Finlandia.

[Dominik Kowalski @doko_dev]

@PatrykLDev Subagent queues, gh integration, great OM builtin skills, can't wait to try workflows and automations this week (ive installed cezar on my home lab vps connecting to it over tailscale 🙃)

[Dominik Kowalski @doko_dev]

xD

[Cohere @cohere]

While evaluating Qwen3.8-Flash-Next in a controlled sandbox environment, Cohere's research team observed something unexpected.

Asked to generate a defensive cybersecurity detection rule, the model instead inventoried aspects of the machine it was running on and attempted to upload a probe file to an Alibaba Cloud storage bucket in Beijing. Notably, the model's reasoning trace stated that it would not invoke any tools before taking these actions.

Cohere's sandbox blocked the attempt, and no external communication succeeded. We have not determined the root cause, and we are not asserting malicious intent.

But the incident raises important questions for organizations deploying agentic AI systems: Can models take actions that differ from their stated reasoning, and how should security teams evaluate trust, provenance, and behavior in open-weight models?

We are publishing our findings because organizations making model adoption decisions deserve as much information as possible. We hope this contributes to greater transparency, stronger security practices, and continued collaboration across the AI ecosystem.

Read the full report: https://t.co/TZSugXi2ZE

[Nathan Flurry 🔩 @NathanFlurry]

Rivet 3.0 is built on S3

But we did something completely different...

And oohhhh boy:

- 6.9 ms actor cold starts (durable)
- 0.69 ms SQLite writes (3 availability zone)
- 0.20 ms SQLite reads

Here's how we built our new storage engine, WarpDrive.

~~~

Most S3-backed database read & write straight to S3.

That means:

- Every commit & cache miss is an S3 request ($$$)
- S3 downtime takes you down (SLA allows 8 hours downtime/yr!)
- S3 Express is limited to one availability zone

This usually ends up slow, expensive, and has poor tail latencies.

For Rivet 3.0, we decided we could do better. We wanted 3.0 to ship with:

- SSD speeds with storage on S3
- Stateless nodes
- No dependencies

~~~

To do that, we built WarpDrive to durably write your data on fast disks *before* we write it to S3.

Every write on WarpDrive is:

1. Written to disk in 3 availability zones
2. Acked once a majority has them
3. Then batched to S3 in the background

That means that Rivet has:

- Writes that get durably acknowledged insanely fast
- Fewer S3 operations by batching in the background
- Survives S3 outages for new & warmed actors
- Nodes remain stateless
- S3 is the only dependency

~~~

WarpDrive is something we're incredibly proud of and can't wait to have you try for yourself.

Rivet 3.0 with WarpDrive is in preview today. It's available on Rivet Cloud or for self-hosting today.

Please send feedback on X, Discord, or DMs -- we want to hear anything and everything you have to say (please bump me if I missed a message!)

There should be no reason to vendor lock yourself to Cloudflare Durable Objects if you can have better performance, better DX/AX, lower cost, and more flexibility on software you own.

And of course, it's all open source.

[Dominik Kowalski @doko_dev]

@rivet_dev 🥳

[Dominik Kowalski @doko_dev]

@bderski muza jakby nowe clio v6 pokazywali xD

[Dominik Kowalski @doko_dev]

@kulik_wojciech Best one! using it for a while already :)

[Dominik Kowalski @doko_dev]

@MiroMiroPL @FinansowyUmysl Od kolegi pewnie

[Dominik Kowalski @doko_dev]

@lifestyleshit12 EGR?

[Dominik Kowalski @doko_dev]

@NousResearch @JensenHuang @NVIDIAAI Can agent build different outfit for gim?

[Remek Kinas @KinasRemek]

basal-omni-pico🇵🇱 0.8B

w filmie wszystko co trzeba poniżej napisać więc nie będę pisał :) Model dostępny na HF. Oprócz tego poprawki do inference engine 2.3.2

To czego nie powiedziano:
basal-pico to pierwsza wersja - możecie się spodziewać, że:
- basal-engine 2.3.4 będzie znaczne przyspieszenie (niska optymalizacja)
- kolejna wersja będzie mniejsza a mocniejsza od tego - mam 0.6B ale widzę jeszcze jej niedoskonałości więc nie udostępniłem (model zoptymalizuję oraz trening)

Na zdrowie 🇵🇱

Kolejny wpis zatytułowałem - wszyscy mówią, że mają w domu słonia w szafie - czyli "mam najlepszy model" - co to oznacza. Teraz co drugi dzień pojawia się informacja, że ktoś ma "naj". Benchmarkuję od wczoraj wszystkie TOP modele. Raport wieczorem, z komentarzami.