Sabitlenmiş Tweet
jonas wiedermann-möller
619 posts

jonas wiedermann-möller
@j0wimo
intern @expsecai | eu/acc | msc data science | ai safety & alignment | curious about tech + ml
🇪🇺 Katılım Mayıs 2019
658 Takip Edilen125 Takipçiler
jonas wiedermann-möller retweetledi

Now would be a great time to release an open source successor to GPT-OSS-120B.
Sam Altman@sama
also, a reason to favor open-source harnesses.
English

Yeah but the issue is when it stays awake it can end up in a death loop and pollute the context which is what you want to avoid.
I previously did the hearbeat loop but personally i find it cleaner to have seperated rolls which the main-thread creates when drafting the handoff.
Basically the main thread says that it's the manager under ID X and that the *new* session is the worker-thread for this task and should ask/end through the steer method.
That way both agents only get activated when they need to and new context is present. Consumes less tokens and personally feels a bit cleaner.
English

Pro tip: when prompting Codex with really difficult /goals, ask it to "write a goal for another thread to achieve this and babysit it until it figures it out"
By doing so, you'll add built-in steering and another layer of taste verification (that's how this video was made)
Nick@nickbaumann_
Asked 5.6 to make a video introducing itself
English

@john__allard ohh i see! tyty, didn't know the reference.
English

@j0wimo this is in reference to his dwarkesh podcast where he said he couldn’t justify the same yolo compute buildouts as unnamed competitors because there wouldn’t be a way to hedge a trillion dollar bet if things slowed down
English

@nickbaumann_ are you able to have one thread manage multiple threads at the same time with this method?
basically controlling multiple goal threads
English

@melvynx Is this new viral trend to fabricate stories «gpt-5.6 deleted everything»?
English

@effi288 Glückwunsch, wichtig für Deutschland und Europa!
Deutsch

📄 Releasing the Soofi S pretraining tech report: a sovereign, open foundation model for German and English
Today we’re publishing the full pretraining tech report and project page for Soofi S 30B-A3B — a Mixture-of-Experts hybrid Mamba model trained on ~27 trillion tokens with deliberately up-weighted German.
What’s in the report:
🏆 Strongest fully open model in our evaluations on BOTH the English and German aggregates — ahead of Olmo 3 32B and Apertus 70B (full methodology in the report)
📋 Radical transparency: complete per-source data accounting, all hyperparameters, training + eval code, checkpoints — everything under permissive licenses
🇩🇪 Trained end-to-end on Deutsche Telekom’s Industrial AI Cloud in Munich — sovereign AI infrastructure on German soil
Soofi S combines frontier-level capability with the highest measured aggregate long-context decode TPS, and unlike full-attention dense baselines maintains high throughput as context grows. The figure plots Capability Index versus measured aggregate decode TPS/GPU at 40K context and batch 32. The Capability Index averages five benchmark groups, i.e., Code, GSM8K, GPQA-Diamond, English aggregate, and German aggregate, after normalizing each group to the best plotted model. Aggregate decode TPS/GPU is measured with a TP=1, one-B200 vLLM latency-subtraction protocol.

English











