joshwa

🙈🎯📈

[joshwa @BldrInvstTech]

calibrating the LPPLS model using Deep Learning: https://t.co/W4nNmGYcta

[joshwa @BldrInvstTech]

@EmanuelDerman Among these dark Satanic mills?

[Steven Strogatz @stevenstrogatz]

Skiing à la Aharonov–Bohm. #quantum_humor

[joshwa @BldrInvstTech]

@karpathy yoink this workflow action if you're yeeting lots of fellow sloperators' slop.

https://t.co/LtQiuu2d9o

[joshwa @BldrInvstTech]

all it takes is one sloperator trusting another sloperator.

introducing `zt-slop`: a tiny GitHub Action/PR check for obvious supply-chain/exfil signals: sketchy deps, lockfile drift, workflow privilege changes, and leaked secrets.

https://t.co/LtQiuu2d9o

[joshwa @BldrInvstTech]

it's like @AndrewYNg 's awesome context-hub cli tool (https://t.co/se3DgvMVRD), but mneme will call the api for you too!

e.g., here is an example where mneme searches the openapi docs from https://t.co/bKRrCtOhZl then executes an http request based on the retrieved docs. https://t.co/yzZl8uotAa

[joshwa @BldrInvstTech]

try mneme. a local MCP server (stdio) that indexes OpenAPI ops, Python + JS/TS symbols, and saved notes. supports auth config as well for private apis. allows an agent to retrieve tools dynamically.

repo: https://t.co/cjeZbIN989
example with @claudeai: https://t.co/vzhrMFwt4C

[kache @yacineMTB]

you can outsource your thinking
but you cannot outsource your understanding

[joshwa @BldrInvstTech]

i watched bugonia recently. clever film. i wrote out some thoughts below. a review, i suppose or the thoughts it evoked from me.

the term bugonia refers to an ancient belief that bees could spontaneously generate from within the carcass of a cow. to a modern audience, this idea appears absurd. we are confident that bees do not originate from within a dead animal. yet the observable result remains the same: bees appear in the carcass. whether they moved in or spontaneously generated becomes, in some sense, an extraneous detail. reminds me of work by Simon DeDeo (@LaboratoryMinds) on how humans build causal narratives to explain complex systems.

this idea becomes a useful metaphor for understanding the character of Teddy in bugonia. over the course of the film, Teddy lays out a set of theories that the audience is encouraged to see as irrational. the film reinforces this framing through moments like the dinner-table conversation about internet echo chambers and targeted online content, where anyone can find information that confirms their preexisting views. when Michelle tells Teddy that he needs help, the audience is likely meant to agree with her. Teddy appears less like a whistleblower than someone lost in conspiratorial thinking.

but the metaphor of bugonia suggests a different way of interpreting Teddy's worldview. in bugonia, the explanation is wrong (bees do not spontaneously generate from a carcass) but the observation itself is not entirely mistaken. there are still bees in the carcass. Teddy's belief that Michelle is an alien may function in a similar way.

by the end of the film, the alien question becomes almost secondary. what matters is that the CEO’s actions on earth have marginalized Teddy, his family, and potentially many others. the film repeatedly emphasizes the trauma that shapes Teddy's life: his mother’s participation in Auxolith’s failed and harmful drug trial undertaken for financial survival, and the abuse he suffered at the hands of his babysitter (who is now a police officer). in both cases, figures who held authority or power over him betrayed his trust in profound ways.

Teddy's seemingly absurd belief system can therefore be understood as a response to these experiences. if the film’s recurring idea is that “in the end there are still bees,” then Teddy's parallel would be: in the end, there is still trauma. whether that trauma originates from an extraterrestrial infiltration of earth or from the actions of a powerful and unaccountable corporation becomes a comparatively minor distinction. the harm itself is real, regardless of the explanation Teddy constructs to understand it.

seen in this light, bugonia is not merely a story about irrational belief. rather, it offers a critique of the social structures that produce marginalization in the first place. Teddy's worldview may appear delusional, but it emerges from genuine experiences of betrayal, exploitation, and institutional failure.

in this way, bugonia suggests that what society dismisses as irrational belief may sometimes be a distorted response to very real harm.

[joshwa @BldrInvstTech]

@AIatMeta @NeurIPSConf @karpathy curious what you think.

[joshwa @BldrInvstTech]

@karpathy still bullish on token level standardization

[joshwa @BldrInvstTech]

@patrick_oshag love the melly andrew

[joshwa @BldrInvstTech]

@karpathy still bullish on token level standardization

[joshwa @BldrInvstTech]

the Toolformer paper from @AIatMeta (https://t.co/bFh1B94HKH) present at @NeurIPSConf in 2023 showed how LLMs could use special tokens (reserved markers distinct from regular words, learn more: https://t.co/XhwNOe33Yp) to invoke external tools/APIs. The pace since then has been rapid!

Across major proprietary foundation models (@OpenAI, @GeminiApp @AnthropicAI) there is convergence on API implementation for their LLMs but an observed divergence in implementation of special tokens in their training data.

This creates a dilemma for developers; should they relinquish context management to the LLM provider? Or, maintain control and invoke tools based on their best guess of the special tokens? Below are the two options reiterated:
1. Provider-Managed (API Abstraction): where the provider handle tool calling via APIs, abstracting the mechanism that intercepts tokens.
2. User/Model-Managed (Direct Token Control): Open models like @AIatMeta's Llama ([INST], see https://t.co/8MH1aMkj1w) & @MistralAI's models ([TOOL_CALLS], see https://t.co/aLwH4VvllM) expose signaling via explicit tokens.

Wouldn't standardization at the token level (a shared markup language for training data) be beneficial, perhaps in addition to a protocol at the API layer? Many might prefer simpler completion endpoints & transparent control via standardized tokens. We see OSS projects like @openbb_finance's OpenBB Agents (https://t.co/pKP5Vb3poT) & @cline's Cline (https://t.co/VRKZkmx1Pc) already opting to manage tool calling themselves.

@AnthropicAI's Model Context Protocol (MCP) (https://t.co/jFn9TEymtm) is a positive step for standardizing connections (their "USB-C for context" analogy 👍), but it doesn't standardize the interaction language itself i.e., the specific tokens signaling LLM intent.

I want this missing piece: a standard, reserved set of signaling tokens ([API_CALL], [ROUTE:TOOL_X], etc.) understood across models. This would enable direct control via completion endpoints. Then all the foundation model providers could just fine-tune next-gen models on these primitives.

Hurdles def exist, primarily conflicts with provider business models built around function-calling API features.

Documented access to existing special tokens could be a start? 🙏

This leads to a fundamental question as LLM workflows grow complex: Where should context & interaction management live? Will provider APIs remain primary, or will developers need the control of standardized, token-level protocols?

What do you think?
❓ Prefer API abstractions or direct token/markup control? Why?
❓ Is the lack of standardized signaling tokens a bottleneck for you?
❓ Is token-level standardization even feasible?
❓ Where should context/interaction management ideally reside – our side or their side of the API?

Let me know below! 👇

#LLM #AI #Toolformer #API #FunctionCalling #Standardization #DeveloperExperience #AIdev #FutureofAI #MCP #OpenSource

[joshwa @BldrInvstTech]

@AIatMeta @NeurIPSConf @karpathy curious what you think.

[joshwa @BldrInvstTech]

@__paleologo La storia è un cimitero di aristocrazie.

[joshwa @BldrInvstTech]

@suchenzang curious what you think about this.

[joshwa @BldrInvstTech]

"The conscious and intelligent manipulation of the organized habits and opinions of the masses is an important element in democratic society. Those who manipulate this unseen mechanism of society constitute an invisible government which is the true ruling power of our country"

-- Edward Bernays, "Propoganda" 1928

[joshwa @BldrInvstTech]

I want a YouTube channel that psychologically decomposes tv commercials.

[joshwa @BldrInvstTech]

@VictorTaelin Dali-esque

[joshwa @BldrInvstTech]

@RobertoDailey1 the insight is promising for MAS. but it does trivialize task decomposition a bit. like, a step in towers of hanoi is always the same thing: move a disk. operationalizing task decomposition in a complex setting is not so trivial. but very interesting nonetheless. great work!

[joshwa @BldrInvstTech]

@choffstein like kinda cringe?

[joshwa @BldrInvstTech]

do humans learn through gradient descent? prob not.
does sequence modeling get you to agi? prob not.

is sequence modeling pretty amazing? yes. the fact that you can get human intelligible text from next token prediction is astounding. i wish we had more commentary on this.

how do wet networks work? where does the analogy with artificial neural networks breakdown?

wet networks are undirected. ANNs are not, at least not in the same sense. forward pass, backward pass is not same as undirected. brains do use electric/chemical signaling across the neural network using synapse dendrites etc. curious to learn more about this.