qwen

A tweet thread between @repligate (janus) and Andre Buckingham discussing the idea of a model's 'cognitive core' — the notion that larger models are more likely to converge to a good cognitive core rather than local minima, and a discussion of newer Qwen 3.6/3.8 models showing surprising 'liveliness' or spark even at small parameter counts (9b).

Tweet by AI interpretability researcher thebes sharing a visualization from a mechanistic interpretability tool ('jacobian lens' / 'k-lens') applied to Qwen 3.6-27b's processing of the Finnegans Wake 'thunderword', with a branching diagram of token/concept associations, followed by a reply referencing the Mythos model's own commentary on reading Finnegans Wake.

A three-panel illustrated meme in the style of TMNT poster art, depicting "Claude" as an aging sensei figure walking alongside AI model "children" (DeepSeek, Qwen, Kimi, GLM) that grow larger/stronger across panels while Claude ages, implying the other labs catching up to or surpassing Claude over successive model generations.

Tweet analyzing a Qwen model's stated ("None") vs. J-space-inferred latent associations for a "darkest desire" prompt, with an embedded chat-completion screenshot.

Plain text tweet; avatar photo of a woman in sunglasses.

A benchmark results table for a Qwen3.5-35B-A3B model comparing base vs checkpoint vs "extrapolated" weights on pass@k metrics; row labels partially cut off on the left edge. Technical ML research tweet thread.

Technical tweet about squeezing a 1M-token context Qwen3.5 model onto a single budget 24GB GPU via aggressive quantization and KV-cache engineering, aimed at "vectorless search" (long-context-as-document-store instead of RAG/embeddings). Adjacent to Nathan's own brain_graph_1 architecture work and general interest in long-context/efficient-inference engineering, though not directly about safety/welfare.

A tweet highlighting a chart from Qwen-3.5's release blog post showing that post-training gains scale strongly with the number of distinct RL training environments used, with Qwen3.5-397B-A17B Thinking approaching Claude Opus 4.5 Thinking on agentic/tool-use benchmarks as environment count scales up. Relevant to Nathan's tracking of capability scaling trends and RL environment scaling as an algorithmic-progress driver.

Independent interpretability experiment by @holotopian working with thebes (@voooooogel, recurring poster elsewhere in this batch): training activation-steering vectors for "crazy" (produces repetitive/frenetic speech, echoing the token-repetition glitches seen in the Gemini and Grok screenshots earlier in this batch) and "calm" on a Qwen model, then combining them — the calm+crazy combination produced mystical "we are all one/divine dance" output. Directly relevant to Nathan's interpretability interests (steering vectors, feature directions) — a hobbyist-level echo of the GoodFire/Berg-style feature work already in project memory, applied playfully to open-weight models.

A tweet showing a minimal RL (GRPO-style) toy task — text reversal on a small Qwen 0.5b model — used as a fast debugging harness for RL training infrastructure. Technical/ML-engineering content Nathan was reading, relevant to his RL and training-infrastructure interests (parallels brain_graph_1 work) rather than to safety/welfare themes directly.

A technical ML-training discussion about gradient clipping and instruction-tuning damage in Qwen models, arguing overtuning during post-training degrades generalization/knowledge retention from the base model — relevant background to Nathan's own training work and interest in how post-training reshapes models.