AI Adam

machine learning @StardustTrade_

[AI Adam @AI_AdamZ]

In GenAI era, I think the answers of two simple questions can reflect your quant ability:
Quant research ability check:
How do you maintain your factors?

Quant development ability check:
How many GPUs are you using?

[AI Adam @AI_AdamZ]

Learning Neural Networks like learning kernels before AI 👀

[Kate Deyneka @katedeyneka]

I'm a very visual person. when I was first getting into ML, I'd try to draw out every concept on pen and paper.

back then I couldn't vibe-code a visualization. but now you can!

here are my favorite ML visualizations I've been saving for a while. take them as inspo for the next complex topic you want to visualize 🧵

[AI Adam @AI_AdamZ]

@banyudongyong @lochan_twt hangzhou

[AI Adam @AI_AdamZ]

Oh

[Watcher.Guru @WatcherGuru]

JUST IN: Citron Research founder and short seller Andrew Left found guilty of securities fraud.

Prosecutors say he illegally influenced share prices through tweets, making $20,000,000

[roife @roifex]

日啖 token 十亿枚

[AI Adam @AI_AdamZ]

@SemiAnalysis_ Shill me all your AI Jokes:)

[SemiAnalysis @SemiAnalysis_]

NVIDIA is proud to announce their partnership with Dwarkesh Patel.

[AI Adam @AI_AdamZ]

@SemiAnalysis_ Shill me all your AI Jokes:)

[AI Adam @AI_AdamZ]

@yminsky I like my btop:)

[AI Adam @AI_AdamZ]

@yminsky I like my btop:)

[Claude @claudeai]

Introducing Claude Opus 4.8: it builds on Opus 4.7 with sharper judgment, more honesty about its own progress, and the ability to work independently for longer than its predecessors.

Available today at the same price.

[Tanishq Mathew Abraham, Ph.D. @iScienceLuvr]

Language Models Need Sleep

"Transformer-based large language models are increasingly used for long-horizon tasks; however, their attention mechanism scales poorly with context length. To handle this, we study a sleep-like consolidation mechanism in which a model periodically converts recent context into persistent fast weights before clearing its key-value cache."

"increasing sleep duration N for our models improves performance, with the largest gains on examples that require deeper reasoning."

[AI Adam @AI_AdamZ]

Amazing 👍

[Muratcan Koylan @koylanai]

Gradient descent for SKILL.md files sounds interesting, maybe a bit complex but it's becoming a real part of agent harness.

SkillOpt is one of the first papers to treat markdown skill files as trainable parameters and provides a proper optimization framework for them.

A few things I learned that you should consider too.

1. The validation gate is the only thing that matters in a self-editing loop.

Held-out set, strict improvement, ties rejected. End-to-end, their best skills land with 1 to 4 accepted edits total. If your "self-improving agent" is accepting most of what it proposes, you're shipping slop.

2. Bounded edits are better than full rewrites. 4 to 8 edits per step is the sweet spot.

Remove the budget and performance collapses. This is the textual analog of learning rate, and it transfers to any LLM-as-author loop. If you're using an agent to refactor your docs, your prompts, or your skills, cap the diff size.

3. Compactness wins. Median final skill: ~920 tokens.

Skills do not need to be long. They need to be high-signal. Most skill files I see are bloated because length feels like effort. It isn't.

4. The harness is becoming less important; the skill is becoming more important.

A Codex-trained skill ported into Claude Code hit +59.7 points on SpreadsheetBench. Procedural knowledge is more general than the runtime that
produced it.

5. Frozen model + trained context is the practical adaptation.

GPT-5.4-nano with a SkillOpt'd skill ≈ frontier behavior on procedural benchmarks. Cheaper, portable, inspectable, zero inference-time cost. This is
the answer to "how do we adapt a frontier model for our domain" for almost everyone who isn't training their own models.

6. Verification is the bottleneck.

Every gate in this paper depends on an auto-grader. That works for benchmarks. It fails for writing, design, and strategy, exactly the open-ended work we want to automate. Whoever builds the verifier for open-ended tasks owns the next stage.

There are also two leassons I learned while shipping v2.3.0 of my Context Engineering Agent Skills repo, measured across composer-2, claude-opus-4-7,
gpt-5.5, and gemini-3.1-pro via the @cursor_ai SDK:
- Description and body are two different surfaces. The router only sees the description. The agent sees the body once activated. They can quietly disagree, and only end-to-end task tests catch it.
- Aggregate accuracy is the wrong unit. When I rewrote three descriptions, the corpus average moved ~1pp. Individual skills moved 23–25pp. Per-skill effect size is where the action is.

Also, in Feb 2026 I shared a piece called Personal Brain OS arguing that the markdown file is a first-class substrate for agent state. SkillOpt is the optimizer-shaped version of that same argument: not "store memory in files" but "treat files as trainable parameters with proper optimization machinery around them." That's the move from static to measured.

The fast/slow split they describe already lives implicitly in the digital-brain-skill repo:
- voice-guide and tone-of-voice.md are slow-state (rarely touched)
- posts.jsonl and bookmarks.jsonl are fast-state

What SkillOpt adds that I didn't have is a protected section invariant, a structural guarantee that fast edits cannot overwrite slow lessons. Removing that mechanism cost them 22 points on SpreadsheetBench. Worth borrowing.

If you're building agents, SkillOpt: Executive Strategy for Self-Evolving Agent Skills is a good paper to read: https://t.co/ZS9SZXQ6Mv

[AI Adam @AI_AdamZ]

Hangzhou, Silicon Valley in China
@vllm_project

[Elon Musk @elonmusk]

Bravo @JeffBezos!

[Elon Musk @elonmusk]

Critique of the 𝕏 algorithm is welcome.

There will be monthly updates of the latest algorithm to GitHub with release notes.

As reminder, you can always choose no algorithm via the Following tab.

[AI Adam @AI_AdamZ]

@yminsky @dwarkesh_sp Who don’t build LLM themselves are no longer quantitative trading firms for sure 💯

[AI Adam @AI_AdamZ]

@yminsky @dwarkesh_sp Who don’t build LLM themselves are no longer quantitative trading firms for sure 💯

[Elon Musk @elonmusk]

@whyyoutouzhele 我的儿子正在学习普通话