Run /usage to see a detailed breakdown of the skills, plugins, mcps, and usage patterns that are draining your context window the most
LLMS
-
Calibration vs. Discrimination in Model Uncertainty
By
–
The calibration vs. discrimination distinction is crucial. A model can know its average error rate without knowing which particular answer is wrong. That is why “just abstain when uncertain” is not enough — poor discrimination creates a utility tax. Faithful uncertainty is a
-
Paper argues metacognition may reduce AI hallucinations
By
–
Trustworthy AI may not require omniscience. It may require epistemic honesty. A new paper by Gal Yona, Mor Geva, and Yossi Matias makes one of the clearest arguments I’ve seen for why hallucinations remain hard — and why the path forward may be metacognition. Hallucinations
-
Opus 4.7 No Longer Needs Plan Mode for Most Tasks
By
–
Opus 4.7 is intelligent enough that it no longer needs Plan Mode for most tasks. I often just jump in, and Claude will ask me questions if it needs to
-
LLM: low margins, intense competition, high expenses
By
–
LLM companies risk being like airlines: low margins, intense competition, high expenses.
-
Gary Marcus on Amazon monopoly vs LLM commodity competition
By
–
sure but Amazon was a near monopoly and LLMs are commodities with intense competition
-
No Japanese models in top rankings, can fine-tune DeepSeek at home
By
–
None of these models rank high at all, no Japanese models even show up in the top. What's your point exactly? I can fine tune DeepSeek on my GPU at home
-
OPUS: Smarter data selection for LLM pre-training
By
–
There is now a smarter way to pick data for training LLMs! Enter OPUS! This is an ICML Oral paper from SJTU, Alibaba, UW–Madison, UIUC, and Mila – Quebec AI Institute. The proposed method dynamically and intelligently selects the most impactful data for LLM pre-training in
-
Critique of outdated mindset on Japan and China AI innovation
By
–
That's a really outdated mindset Japan doesn't even have its own LLM like DeepSeek Its biggest model is Rakuten AI which is a finetuned version of Chinese DeepSeek The cope about China not innovating can't last forever
-
Anthropic’s Mythos model: release plans amidst quality and exploit findings
By
–
"We look forward to making Mythos-class models available through general release" I don't understand Anthropic's strategy regarding Mythos. On the one hand, everyone is saying that Mythos has achieved the expected quality and is finding bugs and exploits that no other model has