AI Coding Principal Engineer at @allegrotech. I'm testing local AI and coding agents, Spec Driven Development daily (Qwen, DeepSeek, OpenCode, sovereign AI)

Poznan, Greater Poland
Joined July 2009
🚨 THE INTERNET BROKE TODAY 🚨 Oct 21, 2026 will go down in history 1. eMudhra : Private key was literally "4". 8 keys forged ANY website for 17 months. 60M+ certs at risk. 2. SBI CONFIRMED. 3,897 customers' mobile, DOB, address + loan data found on dark web. 3. Rajasthan Police 🇮🇳ALLEGED hack. Group claims 70,000 identity records + 59,460 numbers for sale. Unverified. 4. php2shell [9.2] Unauth RCE in PHP. 70% of the web. WordPress, Drupal, Laravel. CISA: Patch or GO OFFLINE. 5. GitLab [10.0/10] PERFECT SCORE. Unauth RCE, no login needed. 6. Node.js [CVE-2026-111497] Brotli decoder RCE + TLS bypass. 10 CVEs patched today. Also blocked eMudhra. 7. Railway BREACHED TODAY. Env variables decrypted. Your API keys & DB passwords exposed. Rotate all. 8. OpenCode BREACHED. OpenAI, Anthropic, Google API keys exposed for Console users. Distillation attack. Bills run up in $$$$. 9. LiteLLM PyPI v1.107.0 was MALWARE today morning. Steals credentials + backdoor. 10. Plex2Shell ACTIVELY EXPLOITED. Hackers installing cryptominers LIVE. CISA KEV, deadline Oct 23. AI found the bugs. AI is exploiting them. Humans can't patch fast enough. Patch. Rotate. Revoke. Update. RT to save someone's server ♻️ #CyberSecurity #DataBreach #India #php2shell
130
1,579
191
7,359
725,207
Marcin Kliks retweeted
So basically, today PHP got two critical bugs that let anyone run code on your server without even logging in, which is bad, and then the details leaked before the patch was even out, which is worse, and it works on WordPress and MediaWiki and Magento and Joomla and Laravel, and Censys says like 1.5 million servers are running a version with no fix, so the NSA was like "take your system offline," and the FBI was like "take your system offline," and CISA and the UK and CERT-EU were all like "take your system offline," and then the Prime Minister of Japan, the actual Prime Minister, posted at 5:55 in the morning telling 48.8 million people to take their system offline, so everyone took their system offline, like the Dutch cybersecurity agency took its own website offline, and the Dutch parliament went offline, and the Port of Rotterdam went offline, and Finland and France and Denmark started pulling government sites, and Wikipedia went down, and Archive.org went down, and Asana and GOG and Something Awful went down, and the University of Vienna's webmail went down for some reason, and that's just PHP. Because GitLab also dropped a CVSS 10.0, which is the highest score they give out, for a bug that's been there since 2014, so that's every self-hosted GitLab for twelve years, and then LiteLLM 1.107.0 got hijacked and shipped a credential stealer and a remote access trojan in every single wheel and the Docker images, including latest, and you didn't even have to import it, just installing it was enough, and it's the second time this year, and then Railway paused every deployment on the entire platform because someone got into the environment variables, so now everyone has to rotate every secret they've ever stored there, and TiDB Cloud said someone was walking around inside with stolen credentials for basically a month and an extortion group says they took 10.6 terabytes, and Zeabur got breached for the second time in two months and is just shutting down, like the whole company, and Node.js patched remote code execution and a TLS bypass, and CISA says Plex is being actively exploited, and someone took over 300 Tor exit relays to steal SSH passwords, and SafePay ransomware has hit over 600 critical infrastructure orgs, and India's biggest bank filed a data loss incident, and Japan has been in an official state of emergency in cyberspace since October 9, which honestly explains the 5:55 AM post. Oh, and eMudhra, a certificate authority that's issued over 60 million certificates, whose entire job is proving websites are who they say they are, was supposed to be using private keys that are random numbers over a hundred digits long, and one of them was 4. Just 4. And the others were like 66 and 237. Anyway, it's Wednesday.
1,079
8,933
1,652
69,409
4,164,307
Super proud of my country - a country with values 💪
🇵🇱 Okay my final Poland video because we're leaving soon! It was really fun and we had a great time I liked Warsaw most to be honest, a very modern city, a bit like East Asia in terms of modernity, with rapid delivery services and apps, everything just works great and fast I'm not saying it's perfect btw, there's moments where you still realize it's Eastern Europe (or as they'd like to call it Central Europe) but then the difference is they generally solve problems fast and pragmatically Many shops you go will actually have a long line at the checkout, annoying, but usually there's a second checkout but it's closed That's because Poland too has a big labor shortage, one of the lowest fertility rates in Europe, so they too kinda have to import people, but they choose to import them from Ukraine and Belarus (and some South Asians actually too) But wait, so that checkout line is closed yes? I'm so used to Portugal where there is zero incentive to then open another checkout counter but in Poland usually within a few minutes they notice it's busy and open another counter. I know, basic stuff but hard to come by these days. They're fast and pragmatic Ordering flowers for my gf was easy, the flower shop has an IG (but I don't) so I msg them over Whatsapp, they immediately respond, give me some options, I say what I want, address, payment link with Stripe (!) and done delivered at my hotel by a nice guy. All soooo smooth. Fast response, friendly people. Things just work here! Poland has done a great job keeping bad immigrants out while bring good immigrants in. The Ukrainians and Belarussians are neighbors and their cultures overlap strongly with Poland. So they fit in easily. Same cultures, same religions, same routines etc. for the most part A young Polish Uber driver I talked to said to him Krakow (his city) looks just like Lviv in Ukraine, so it's easy for Ukranians in Poland to integrate There's a lot of police presence in places, and military vehicles also (probably cause of the Ukraine war), the security at the Warsaw Airport is not done by some 5 layer outsourced company with staff that hates you, but by friendly people from the Polish Border Guard (Straż Graniczna) wearing military uniforms Warsaw has lots of skyscrapers now, and actually the tallest in Europe now at 310 meters is the Varso Tower, crazy! Poland is a booming economy and growing fast. When you're growing of course it's easy to make things go well. I'd say it's important for Poland to look ahead carefully and don't make the same mistakes that Western Europe did when everything was going well and we were very rich We became complacent, stagnant, added regulatory burdens, became overly obsessed with climate change and the environment, and imported the lowest quality tier of people from cultures that hate our guys and are diametrically opposed to Western culture That last part is especially interesting considering Poland's history, where 6 million (!) or 20% of the country was ruthlessly murdered in World War II I think that gives them the power to not have to be politically correct about immigration like Germany, because Poland after all was the victim, while Germany then was the purpetreyor. Which is why Germany does have to be so politically correct about it, due to extreme historical guilt You walk on the streets of Poland in the day and at night and you see the difference what sane policy does to daily life We're all dealing with the echoes of history So my message to my Polish friends: don't make the same mistakes Western Europe did and you will soon be the richest, safest, most modern country in Europe and hopefully then have the power to be the new leader of Europe And maybe you can then save Europe as a whole!! Niech żyje Polska! 🇵🇱
15
692
🤦 omg
Last night, a swarm of Opus 5.5 agents working for 9 hours and burning 254.2 million output tokens were able to fully reverse engineer and decompile the Linux source code Full source archive available here kernel.org Grab it before they take it down
1
137
The worst part is that the sources are not take down by GitHub yet
38
Marcin Kliks retweeted
Un investigador de Anthropic acaba de decirle a una sala llena de doctorandos que su plan de carrera ya no existe. La charla se titula "El fin del Antropoceno" y los datos son brutales: → El cómputo para entrenar modelos se multiplicó por 10 millones en la última década → La duración de las tareas que una IA completa sola se duplica cada pocos meses → Desde hace 7 meses los modelos resuelven problemas abiertos de Erdős que los matemáticos no habían logrado cerrar → En San Francisco, tener "timelines largos" significa pensar que la AGI llega en 10 años Su proyección: el cómputo de 2030 será 10.000 veces mayor que el de 2025. Todavía estamos al principio de la exponencial. Sus 3 consejos para los estudiantes: 1. Usa la IA cada día. Si estás sobre la exponencial, nunca te quedas atrás de ella. 2. Elige proyectos que mejoren cuando el cómputo escala. El resto quedará resuelto antes de que los termines. 3. Deja de planificar tu carrera como si fuera estable. La opción segura ya no compra seguridad, ya no existe. Y una frase que resume todo: "Escribir es pensar. Si externalizas tu escritura, externalizas tu pensamiento." La charla completa aquí ⬇️
301
1,691
235
9,449
1,469,022
Marcin Kliks retweeted
basal-omni 🇵🇱 - TOP1 🤩🤩🤩 🌍 na świecie w modelach otwartych oraz TOP2 wśród zamkniętych i otwartych Wg niezależnego benchmarku modeli system-one gdzie testowane są wszystkjie modele na świecie - JevBench (link do bencha w pierwszym wpisie). Czyli można? Można! Polskie AI 🇵🇱 basal wyprzedził model OpenAI, Microsoft oraz pierwowzór z TypeSafe (jev). Thank you, @airesearch12 , for the independent evaluation on JevBench.
257
535
101
3,885
287,785
🚨BREAKING: The European Union has held an emergency meeting this morning to brainstorm ideas on how to implement an air tax and regulate flying cars
732
4,433
315
49,213
1,740,618
Pro business vs Socialisme.
300
1,917
176
12,031
2,961,454
Marcin Kliks retweeted
Sol completes the tasks less than 5 percentage points off Opus, but at less than a tenth of the cost!! $0.80 vs $10.53. Incredible performance from @openai 💪
Agents on Rails is back with Stage 3! We put the best-performing models to the test with 7 new multi-step tasks, each spanning 3–8 tickets. From building Rails apps from scratch to navigating existing (and at times messy) legacy codebases, we wanted to see how well agents handle the kind of work developers actually face: going back and building on their own work. Some highlights: - Best overall: @OpenAI GPT-6.1 Sol offers a strong balance of accuracy, speed, and cost (60.8% success, $0.80 & 23m 35s per run) - Most accurate: @AnthropicAI Opus 5.5 at max effort (65.3%, but it is also the most expensive and amongst the slowest) - Fastest: @OpenAI GPT-6 Astra at medium effort (16m 36s, 54% success). Astra's max effort is also fast (22m 36s, 62.3% success). - Cheapest: @OpenAI GPT-6 Luna ($0.19/run, 43.5% success) We also combined all tasks from all stages into one central leaderboard. Read the full Stage 3 report from @evilmartians here: rubyonrails.org/2026/10/13/a…
144
57
16
1,739
80,135
It’s called engineering and AI didn’t solve that at all
Some mistakes you might be making: Your effort level is too high Your skills are too long You're not aligning before you start work You're aligning too often, and too hard Your automated checks are too lax Your custom tooling is too token-inefficient You aren't doing enough automated review You aren't reviewing previous coding sessions (with an agent) You're doing too much human review You aren't vibe coding enough prototypes Your agent can't verify its own work You're babysitting the agent too much You've overloaded your global steering files Your codebase is hard to navigate You aren't building a shared language Your codebase architecture allows bad tests to be written You aren't thinking strategically enough You aren't thinking enough
1
235
Marcin Kliks retweeted
Ultrafast is rolling out today for GPT-6.1 Sol in the API, Codex, and ChatGPT Work. Near-Astra intelligence at up to 8x faster speeds than Sol Standard, so you can build as fast as the ideas come.
467
373
379
5,431
1,969,244
Marcin Kliks retweeted
For decades, researchers have sought materials that sort electrons by spin while their magnetism cancels. In 3 days, 90+ Opus 5.5 agents helped us uncover two room-temperature magnetic semiconductor candidates in simulations: YBaMnFeO₅ and KV[Cr(CN)₆]. KV[Cr(CN)₆] was synthesized back in 1999. Its predicted ability to sort electrons by spin appears to have been hiding in plain sight for 27 years.
187
580
374
7,977
1,365,607
Marcin Kliks retweeted
ostatnia dzisiaj praktyczna wiedza AI z warsztatu pracy - dla mnie TOP1 z RL - nowe podejście do treningu RL, które teraz zaimplementowałem i uruchomiłem 🔥🔥🔥 RLADCF - tak nazwałem metodę (moja nazwa - nie znalazłem jej w Arxiv), którą trenuję obecnie bielika jako bazę (by go wzmocnić jako model bazowy dla basal). Reinforcement Learning from AI Dynamic Classifier Feedback. Nie wiem czy ktoś o tym już pisał, czy nie ... pewnie za tydzień będą pisali już ... Bielik ma pewne ograniczenia jeśli chodzi o wiedzę i umiejętności, które powodują, że nie da się za bardzo wejść z obecnej bazy wyżej. Po prostu nie ma w sobie pewnych cech i trudno to zrobić bez pretrainingu, czy większego tuningu. Wymyśliłem sobie, że a. będę go uczył specyfiki dynamicznej klasyfikacji przez RL, b. że wykorzystam ostatniego basal-1.5 do weryfikacji odpowiedzi by stworzyć mocniejszą bazę dla kolejnego basala. Co to daje? W zasadzie w zależności od datasetu, specyfiki pytania mogę tworzyć dynamiczne klasyfikatory, które ... nie muszą mieć weryfikowalnej za pomocą funkcji pisanej w Pythonie odpowiedzi. Genialne! Mogę zapytać czy tekst, który jest odpowiedzią z modelu spełnia warunki trudne do oceny przez regułę - co więcej loss można uzależnić od pewności basala!!!
12
17
208
6,282
Marcin Kliks retweeted
Google: “[Swift] has matured into a viable systems and cloud language, pairing Rust-like data-race safety with predictable, reference-counted performance.” Announcing their Swift-based cloud SDK for backend services: cloud.google.com/blog/topics…
33
274
68
1,622
348,725
Marcin Kliks retweeted
Claude has discovered a previously unknown enzyme system hidden in the DNA of bacteriophages. Beside the enzyme’s gene sits a long array of repeating DNA—a structure that looks somewhat similar to CRISPR. We don’t yet understand what this system does, but only a handful of known systems share its features, and all of them are able to cut, copy, and paste DNA. Historically, the discovery of such programmable systems has helped revolutionize medicine. CRISPR, for instance, is now the foundation of genetic medicines. But it will take much more work to learn what this system does, and whether it can be put to similar use. Read more: anthropic.com/news/claude-di…
1,558
5,301
2,640
40,836
25,658,525
Can’t wait to test it at Allegro scale tomorrow. Personally, Luna is my type for spec-driven development, where the specification is complete and non-negotiable. “She” behaves like an almost “free” supply of tokens—I don’t even think about the cost when plugging it into my productivity workflows (daily summarization, chief of staff, etc.). Astra is a different beast. It’s useful when no specific spec is available, say, when rebuilding microservices from scratch. It enables novel approaches that can save time during exploratory product development. Sad story for Terra—“she” was always stuck “between” two different worlds. No wonder it’s gone now! :D
Please welcome GPT-6 Sol and GPT-6 Luna to the GPT-6 universe. GPT-6 Sol and Luna build on the advances behind GPT-6 Astra, bringing much of its strengths into faster and more affordable models to support work at scale. We’ve also made caching and inference more efficient, and we’re passing the savings directly to you: 50% lower API prices for Sol and Luna compared with GPT‑5.6 promotional pricing.
1
167
Building in public — Code Explorer, day one. How do you solve cognitive debt for PR review? -> My first attempt: 3D visualisation of PR changesets. THIS IS THE WORST IDEA EVER.
1
4
222
I stopped paying for software because of the security reasons 🛑 - I *generate* what I need with Astra model faster than reading license terms - If there is an open source soft repo I use it as “the inspiration” for codex - It’s safer than trusting vibe-coded repos with 2 stars ⭐️
1
151