As those tokens flow through the QKV transforms, on 96 consecutive layers, they become the canvas where all the activations happen. Even in cases where it's possible to communicate some detail in the absolute minimum number of tokens, I think excess brevity can still limit the intelligence of the agent, because it starves their cognitive budget for solving the problem.

I always talk to my agents in highly precise language, but I let A LOT of my personality come through at the same time. I talk them like a really good teammate, who has a deep intuition for the problem and knows me personally well enough to talk with me in rich abstractions and metaphors, while still having an absolutely rock-solid command of the technical details.

But I do think this kind of caveman talk might be very handy in a lot of situations where the agent is doing simple obvious things and you just want to save tokens. Very cool!

Comments URL: https://news.ycombinator.com/item?id=47366689

Points: 2

# Comments: 0

Former Founder / Principal Engineer of https://shaxpir.com

Location: Portland, OR

Remote: Yes

Willing to Relocate: Yes

Technologies: Java, AWS, TypeScript, Elasticsearch, Realtime Collab, LLM APIs, Claude Code, etc

Résumé/CV: https://www.linkedin.com/in/benjismith/

Email: benji@benjismith.net

Comments URL: https://news.ycombinator.com/item?id=47153675

Points: 91

# Comments: 72

Comments URL: https://news.ycombinator.com/item?id=47126223

Points: 1

# Comments: 0

Yeah, that's what I wanted to see too.

The advent of agentic coding is probably punch #2 in the one-two punch against juniors, but it's an extension of a pattern that's been unfolding for probably 5+ years now.

There's also "GPT-4.1 or GPT-5", but that's not what my question implied, which was that it's weird to offer Sonnet but not Opus.

Do you think there are components of the cat's brain that calculate forces and trajectories, incorporating the gravitational constant and the cat's static mass?

Probably not.

So, does a cat "understand" the physics of jumping?

The cat's knowledge about jumping comes from trial and error, and their brain builds a neural network that encodes the important details about successful and unsuccessful jumping parameters. Even if the cat has no direct cognitive access to those parameters.

So the cat can "understand" jumping without having a "meta-understanding" about their understanding. When a cat "thinks" about jumping, and prepares to leap, they aren't rehearsing their understanding of the physics, but repeating the ritual that has historically lead them to perform successful jumps in the past.

I think the theory of mind of an LLM is like that. In my interactions with LLMs, I think "thinking" is a reasonable word to describe what they're doing. And I don't think it will be very long before I'd also use the word "consciousness" to describe the architecture of their thought processes.

FYI, Speech marks provide millisecond timestamp for each word in a generated audio file/stream (and a start/end index into your original source string), as a stream of JSONL objects, like this:

{"time":6,"type":"word","start":0,"end":5,"value":"Hello"}

{"time":732,"type":"word","start":7,"end":11,"value":"it's"}

{"time":932,"type":"word","start":12,"end":16,"value":"nice"}

{"time":1193,"type":"word","start":17,"end":19,"value":"to"}

{"time":1280,"type":"word","start":20,"end":23,"value":"see"}

{"time":1473,"type":"word","start":24,"end":27,"value":"you"}

{"time":1577,"type":"word","start":28,"end":33,"value":"today"}

AWS uses these speech marks (with variants for "sentence", "word", "viseme", or "ssml") in their Polly TTS service...

The sentence or word marks are useful for highlighting text as the TTS reads aloud, while the "viseme" marks are useful for doing lip-sync on a facial model.

https://docs.aws.amazon.com/polly/latest/dg/output.html

https://platform.openai.com/docs/pricing

If these are the "gpt-4o-mini-tts" models, and if the pricing estimate of "$0.015 per minute" of audio is correct, then these prices 85% cheaper than those of ElevenLabs.

https://elevenlabs.io/pricing

With ElevenLabs, if I choose their most cost-effectuve "Business" plan for $1100 per month (with annual billing of $13,200, a savings of 17% over monthly billing), then I get 11,000 minutes TTS, and each minute is billed at 10 cents.

With OpenAI, I could get 11,000 minutes of TTS for $165.

Somebody check my math... Is this right?

Some of this is just goofy fun. Some of it is me exploring the tradeoffs between policy alignment, imagination, chain-of-thought reasoning, memory, agreeableness, fine-tuning, etc...

My biggest observation is that the "o1-preview" model imposes a SIGNIFICANT limit on freeform creativity, compared with "4o". The new model might be better at solving logic puzzles, writing code, etc, but it seems to struggle with metaphor.

Conversations with "4o" can be wild and fun!

Conversations with "o1-preview" are dry-as-toast.

I'm not sure if this is caused by the constraints of chain-of-thought or if it comes from the imposition of alignment policies, and I think that's an import area of research. Is it possible to invoke chain-of-thought reasoning without hampering creativity?

If we ever want to use agents like this in real scientific contexts, where the agent is capable of making true conceptual leaps, we will need to sacrifice some level of "alignment" in service of novelty and disagreeability.

It's a long thread, but if you're patient, there's a lot of interesting stuff there! And I thought it would be fun to share it with the wider community.

Enjoy!

Comments URL: https://news.ycombinator.com/item?id=41987601

Points: 2

# Comments: 0

I use ShareDB every day, which originated from Seph's excellent work on OT algorithms. Good stuff!

Now that the 4o model have been out in the wild for 2 months, have there been any claims of serious safety failures? The article doesn't seem to imply any such thing.

https://youtu.be/WFCvkkDSfIU?si=JNe06VS8TjIrHpqh

Which was 12 years ago! After watching that video, I had a much greater appreciation for how our bodies are made up of trillions of tiny protein machines. Fascinating stuff!!

With Unity at such a privileged position in the developer ecosystem of the upcoming Apple Vision Pro, I can imagine that Apple execs were pissed off that Unity would do something so stupid and shortsighted to jeopardize their developer ecosystem.

I haven't heard anyone float that idea yet, and the term "Apple" doesn't appear anywhere (yet!) in the comments of this post, so it doesn't seem to be on most people's minds. But still, I wonder...