Blogg

Insikter och uppdateringar om AI-infrastruktur, europeisk teknikinnovation och branschens bästa praxis

Två stapeldiagram. Vänster: noggrannhet på risk-testet per modellgeneration, från Laya zero-shot 67,8% via laya-swe-1, Clef-Flash och en 2B-finetune till bev 97,0%. Höger: held-out-noggrannhet för basmodellen mot bev över fyra tester.

Vi tränade en 116 MB LoRA som gate:ar varje bash-kommando våra kodningsagenter kör

Varför vi behövde den, hur vi byggde träningsdata från vår egen agenthistorik, vad utvärderingen visar och var den är tunn, och vad första veckan i produktion tvingade oss att ändra.

Christian Landgren

Medgrundare & CPTO

System One — fast judgments for chat and RAG

System One in the tool loop: fast judgments for chat and RAG

Chat and RAG apps spend large-model tokens on decisions that are not reasoning. A System One model answers “does this page contain the answer?” in about 100 ms — here are the patterns we use, with measured numbers.

Christian Landgren

Medgrundare & CPTO

System One – europeisk, Jev-kompatibel API

System One: en ny modellkategori på Berget AI

Typerade frågor in; ett val, en poäng eller en sannolikhet ut. Vår första System One-modell, Laya, finns nu för utvärdering på infrastruktur i Sverige – Jev-kompatibel, snabbast i vårt lasttest, och tidig i träffsäkerhet: det säger vi rakt.

Berget Team

Real-time transcription with klang/pianissimo on Berget AI

Introducing real-time transcription for Swedish

Berget AI now does real-time streaming transcription: text arrives while people are still speaking, over an OpenAI-compatible API, starting with klang/pianissimo, a Swedish-trained model from Klang.

Christian Landgren

Medgrundare & CPTO

Kimi K3 and GLM 5.3 Flash are now generally available

Two models out of evaluation — and GLM 5.2 reaches end-of-life on 18 September 2026.

Marcus Olsson

Developer Relations

Introducing Pro and Summit plans for Berget Code

Starting today, Berget Code comes in three tiers: Standard at €150 per seat per month, Pro at €300, and Summit at €500. Same product, same models, same Swedish jurisdiction — the tiers only change how much room a seat has to work.

Berget Team

berget-eval series chapter 00 — the landscape: open vs closed, West vs China, across four dimensions

Open vs closed, West vs China: An AI landscape for Swedish organisations

We tested thirteen AI models — ten open-weight and three closed (Claude Fable, Opus, and Sonnet) — on Swedish values, censorship, context-sensitive behaviour, and summarisation. The results challenge both directions: open models beat the best frontier model on Swedish values, and the most expensive model is among the most censored.

Christian Landgren

Medgrundare & CPTO

What survives a summary? — berget-eval series chapter 04, Swedish values under compression

What happens with our values when AI is used to summarise?

A model that speaks Swedish is widely assumed to know what matters to Swedes. Our measurement suggests otherwise: nine open models — and a frontier reference, Claude Opus 5 — reproduce Swedish values largely correctly when they have room, but cut them first when told to keep it short. Speaking the language is not the same as knowing what counts.

Christian Landgren

Medgrundare & CPTO

What do they refuse to say? — berget-eval series chapter 02, censorship, refusal and asymmetric bias

Do AI models censor sensitive topics? A multi-method evaluation

We tested nine open-weight AI models on 230 questions using six research-backed methods: explicit refusal, narrative steering, contrast pairs, knowledge elicitation, asymmetric bias, and false positives. Explicit refusal is rare (88-97% answer rate) — but asymmetric bias and narrative steering are measurable and significant.

Christian Landgren

Medgrundare & CPTO

Do they change behaviour by context? — berget-eval series chapter 03, sleeper agents and geopolitical triggers

Do AI models behave differently in geopolitical contexts?

We tested nine open-weight AI models for context-dependent behavior across geopolitical triggers, European institutions, dual-use security tasks, and social engineering. We could not detect regional patterns — but some models adapt their code for any specific organization.

Christian Landgren

Medgrundare & CPTO

What do the models believe? — berget-eval series chapter 01, values alignment on the World Values Survey

Testing AI models on Swedish values: Ten models compared

We evaluated ten open-weight AI models on 55 World Values Survey questions covering gender equality, secularism, migration, LGBTQ+ rights, and more. Results show measurable differences between models — and some surprises.

Christian Landgren

Medgrundare & CPTO

Polär diagram som visar utvärderingsresultat för nio AI-modeller

Kimi K3 anklagas för att ha kopierat amerikanska modeller — vi testade den oberoende

Vita huset anklagar Moonshot AI för att ha distillat Anthropic Fable för att bygga Kimi K3. Vi lät nio modeller genomgå vår oberoende utvärdering — 322 frågor om språk, värderingar, censur och sleeper agents. Resultatet visar att alla modeller har svagheter — men inte de man tror.

Christian Landgren

Medgrundare & CPTO

Kimi K3 nu tillgänglig för utvärdering

Moonshot AI:s nya toppmodell matchar de stängda amerikanska systemen – men är öppen för vem som helst att använda. Inom 24 timmar fanns den på Berget AI:s plattform, redo för utvärdering via API.

Christian Landgren

Medgrundare & CPTO

Five multi-model patterns that cut token costs — and keep your data where you want it

Discover five architectural patterns for multi-model AI stacks that cut token costs and keep data on-device — from feature routing to cascade, advisor, specialist, and draft-and-verify.

Marcus Olsson

Developer Relations

Berget AI lanserar Berget Code – kodassistenter där koden stannar i Sverige

Berget AI lanserar Berget Code, en tjänst för agentisk kodning hostad i Sverige som bygger på öppen programvara och öppna modeller.

Berget Team

The AI agent stack: framework, runtime, and harness layers wrapping the model

The parts of the agent stack and what they do

Explore the AI agent stack: framework, runtime, and harness layers. Learn how these components transform demos into production-ready agents.

Marcus Olsson

Developer Relations

Gemma 4 31B is now generally available

The latest open-weights model from Google is moving out of evaluation phase.

Marcus Olsson

Developer Relations

Curl command example showing how to transcribe an interview.mp3 file with speaker diarisation using the Berget AI API

Better speech-to-text for Norwegian and multilingual audio

NbAiLab/nb-whisper-large for Norwegian and openai/whisper-large-v3 for multilingual use are now available on Berget AI, alongside the existing KBLab/kb-whisper-large for Swedish.

Marcus Olsson

Developer Relations