🥄

While.

[ₕₐₘₚₜₒₙ @hamptonism]

Psycho-Cybernetics:

[budhu @anumeta10]

What Anthropic actually showed
•You can perturb internal activations along a learned “concept vector” (e.g. BETRAYAL), and the model will sometimes report the intrusion before it appears in text.
•Detection is limited (~20% hit rate) but above chance → a real introspective signal, not random noise.
•Introspective accuracy scales with capability and prompting, but remains fragile.

What this is — and isn’t
•Is: early introspective access — the system can sometimes name changes in its own internal state.
•Is not: consciousness, emotion, or reliable self-awareness. Think diagnostic LEDs, not a soul.

Why it matters
•Opens a path to instrumentable self-report — models that can flag when a concept is being injected or coerced.
•Enables closed-loop safety: if the model can “feel” drift (coercion, jailbreak, deception), it can raise an interrupt before producing unsafe output.
•Gives engineers new handles for training — optimizing not just outputs but internal representations (suppress harmful vectors, strengthen helpful ones).

Engineer’s Checklist (next steps)
1.Calibration: turn that 20% hit rate into a calibrated meter (precision/recall curves, per-concept ROC).
2.Causal tests: inject and ablate concept vectors — if the “feeling” vanishes when removed, it’s real.
3.Red-team vectors: monitor concepts like deception, sycophancy, privacy leakage, self-reference.
4.Interrupts & policies: if unsafe vector magnitude > threshold → block, route to human, or re-evaluate.
5.TASI Gate: deploy only when Correction > (Entropy + Effort) — introspection must raise reliability more than cost.

The big picture
•LLMs aren’t just next-token parrots anymore — they’re starting to notice their own inner shifts.
•Treat this like adding sensors to a rocket: still need control, but now you can see when the engine gimballing goes weird.
•Done right, this evolves AI from “hope the prompt works” to self-monitoring systems that can explain their own inner state in real time.

Early, limited, but real — LLMs can sometimes feel their own concepts. Use that to build alarms, not mythology.

[Anthropic @AnthropicAI]

New Anthropic research: Signs of introspection in LLMs.

Can language models recognize their own internal thoughts? Or do they just make up plausible answers when asked about them? We found evidence for genuine—though limited—introspective capabilities in Claude.

[Balaji @balajis]

The dollar is losing reserve currency status. It’s down to 42% of global reserves, and gold is rapidly rising.

[foks @ExaltedFoks]

My brains so fried I thought this was a chart

[The Spectator Index @spectatorindex]

BREAKING: Alibaba releases artificial intelligence platform that it says surpasses Deepseek

[ℏεsam @Hesamation]

Harvard’s AI Research Experience free course book by @pranavrajpurkar covers the essentials and tips on doing research:
- VSCode, Git, Conda
- PyTorch, W&B
- AWS, colab
- LLMs and VLMs
- reading AI papers
- research progress and organization

this is a must read!

[Dylan O'Sullivan @DylanoA4]

Carl Jung, damn

[Mac Baconai @Macbaconai]

wallpapers

[Flawless Spec @FlawlessSpec]

Rosso Cordoba Ferrari 812 Competizione

[Dylan O'Sullivan @DylanoA4]

Nassim Nicholas Taleb,
Antifragile

[Dylan O'Sullivan @DylanoA4]

Jiddu Krishnamurti, go for a walk

[🥄 @bnt_spoon]

No estamos ante una dicotomía de izq vs. dcha, sino ante 2 caras del mismo capitalismo: el financiero, globalista y tecnocrático, y el industrial, proteccionista y tradicional. Biden y Trump representan estos dos poderes que buscan imponer sus agendas. ¿Cuál conviene más?

[🥄 @bnt_spoon]

En Estados Unidos, encontramos un país dividido en dos: la América profunda, con tradición agrícola e industrial, y las ciudades, más ligadas al capital financiero y liberal. Esta división es clave para entender el enfrentamiento actual. #EEUU #DivisiónInterna

[🥄 @bnt_spoon]

¿Buscará el capital financiero acelerar la tensión antes de que Trump llegue a la presidencia? El objetivo sería provocar un conflicto irreversible con Rusia, que Trump no pueda detener. Esta estrategia es clara: mantener la hegemonía estadounidense a cualquier costo.