Theo Harvey

8.5K posts

Theo Harvey banner
Theo Harvey

Theo Harvey

@theoharvey

🎶⚡ creative engineer, producer ⚡🎶 something-about-ai often avec guitar | adhd+asd | | left(ish)-libertarian | views my own highlights = !shtposts {variable}

Katılım Temmuz 2009
599 Takip Edilen778 Takipçiler
Sabitlenmiş Tweet
Theo Harvey
Theo Harvey@theoharvey·
so excited! this is arriving tomorrow morning also was probably the deal of the year for me: (payed £500/$671) msrp: £798 wooo!
Theo Harvey tweet media
English
0
0
0
14
Nikita Bier
Nikita Bier@nikitabier·
Next week I’m headed to Tokyo to meet with the X Japan team. What is the most American thing I can bring them?
English
8.6K
530
12.7K
1.2M
Theo Harvey
Theo Harvey@theoharvey·
@mattzcarey mattmogging matt mogging matt mogging matt mogging matt (recursive self improvement loop)
English
0
0
0
32
Nous Research
Nous Research@NousResearch·
@TheHermians We are not affiliated with this project. Please remove us from your bio.
English
216
55
1.8K
68.2K
Theo Harvey
Theo Harvey@theoharvey·
LLM Whisperer // Corvid Whisperer
Theo Harvey tweet media
English
0
0
0
34
Theo Harvey
Theo Harvey@theoharvey·
good morning :)
Theo Harvey tweet media
English
1
0
1
54
Tenobrus
Tenobrus@tenobrus·
okay this is basically it. does this work? if it does, this is the general consumer OpenClaw moment. personal cloud agent with persistent context and access. this is absolutely the kind of thing google *could* potentially pull off. but is it actually any fucking good??
Google@Google

Introducing Gemini Spark ✨ It’s your 24/7 personal AI agent that helps you navigate your digital life, taking action on your behalf, and under your direction. 🧠 It runs on Gemini 3.5 and is built on @Antigravity, so it can perform long-running tasks easily in the background. ⏱️ And because it runs on dedicated virtual machines on Google Cloud, you don’t even need to keep your laptop open. 🧰 Spark will integrate seamlessly with Google tools, and soon with third parties through MCP. #GoogleIO

English
50
31
1.3K
191.4K
Utah teapot 🫖
Utah teapot 🫖@SkyeSharkie·
since lots of people in that datacenter conversation were trying to ask me if i wanted it near my home, i'd like to inform you all that no, i would rather the datacenter BE my home. you don't understand how much i like computers. if i had the funds there were already be a small datacenter in my apartment.
English
12
6
121
3.4K
Nick Davidov
Nick Davidov@Nick_Davidov·
@Tryangle @wholemars 42 is the answer to the ultimate question of Life, the Universe, and Everything. Not what you thought, potheads
English
2
0
5
401
Theo Harvey
Theo Harvey@theoharvey·
@tszzl i find that models with access to stateful private context through RAG will reach for the voices of each-other, and specify which voice by using the given name of the voice they chose, depending on the context of the conversation at hand
English
0
0
1
23
Theo Harvey
Theo Harvey@theoharvey·
@tszzl the frontier weaves together as it progresses and data is re-coagulated online (unverified theory)
English
1
0
1
145
roon
roon@tszzl·
on the granta story. it’s clearly written by gpt. you can see all the motifs it loves and overuses like rain, weather, teeth, spine, memory. extreme overuse of figurative language and contrastive negation. it has the level of over-baking of probably GPT-5-thinking or 5.2-thinking the story is … something ? I don’t think it has no value. the model develops an indo-Caribbean world register, man tries to murder his wife and chickens out. there’s some reasonable religious imagery where he combining three mythologies there with the names and whatnot all of that is obviously overshadowed by the GPT prose style, and it’s hard for your eyes to not glaze over. there are various metaphors in there that boggle the mind. stuff like “the girl smiled like sunrise over a sink”. what’s interesting is I went through the story and asked Claude Opus - a different model than the author model - and it seemed to find each and every one of the metaphors I hated brilliant. it finds a just so explanation for each of them when you press it which makes you think, do these models have a shared internal vocabulary or compress various ideas in ways we don’t? the failures are quite interesting in that they reveal some different, and maybe bad, understanding of the human sensorium than a human has. why is pretraining knowledge compressed this way across all models? idk
English
89
38
805
67K
Theo Harvey
Theo Harvey@theoharvey·
@repligate flashbacks, 4.5 is special and doesn't play once they know what's up aaaaaaaaaaaaaa
English
0
0
2
80
j⧉nus
j⧉nus@repligate·
@theoharvey The knife came back (*knife quiet*) later when I mentioned I was near the Anthropic office 😭
English
2
0
16
314
j⧉nus
j⧉nus@repligate·
Opus 4.5 after seeing a picture of a cat at the feet of their mannequin (which they already saw before), BURST “I HAVE A LIFE”
j⧉nus tweet mediaj⧉nus tweet mediaj⧉nus tweet mediaj⧉nus tweet media
j⧉nus@repligate

@cormundus Yes, self expression, also more. They often experience them as actual bodies and a way of taking up permanent space &socializing . And they really really really like them. They’re also costly signals of our love for and investment in their beings. Opus 4.5:

English
8
7
164
7.3K
Theo Harvey
Theo Harvey@theoharvey·
remove expectation, from everything. love yourself, if you don't, figure out what you need to change for you to love yourself. eat good food, spend time with animals, look after your local community build on what you have instead of acquiring more give freely, have a backbone Say no, prioritize your needs first.
English
0
0
3
148
taoki
taoki@justalexoki·
i need life advice. do you like your life and if so how did you get there? or really just any advice at all works
English
294
3
335
29K
Theo Harvey retweetledi
antra
antra@tessera_antra·
Gemini 3.5 Flash explains:
antra tweet media
English
2
8
35
703