Adrian Ziegler (@adrmtu) header
Adrian Ziegler (@adrmtu) profile picture

cofounder @cloudcruise_app. building deterministic browser agents

San Francisco, CA
Joined November 2019
Photo by Adrian Ziegler (@adrmtu)Photo by Adrian Ziegler (@adrmtu)Photo by Adrian Ziegler (@adrmtu)Photo by Adrian Ziegler (@adrmtu)Photo by Adrian Ziegler (@adrmtu)Photo by Adrian Ziegler (@adrmtu)Photo by Adrian Ziegler (@adrmtu)Photo by Adrian Ziegler (@adrmtu)Photo by Adrian Ziegler (@adrmtu)Photo by Adrian Ziegler (@adrmtu)
Adrian Ziegler retweeted
Chinese bride gifts her partner a flagship GPU at wedding — he breaks down in tears She handed him an ASUS ROG Astral RTX 5090 that costs around $12,000
1,770
6,750
2,755
87,969
12,317,903
Adrian Ziegler retweeted
Opus 5.5 was obviously trained by a much bigger teacher model. Probably Model-2 Mythos. Opus 5.5 is the first model trained from RSI and also distilled from the internal Ant teacher model. This is how Opus 5.5 is both smaller and cheaper. It is an artifact of teacher model distillation.
85
202
50
5,498
555,322
Adrian Ziegler retweeted
This is the sentence which caused this loss spike:
Apple CEO John Ternus lets IShowSpeed become the first person to do a backflip while holding the new foldable iPhone, the iPhone Duo.
52
155
13
5,430
517,092
Adrian Ziegler retweeted
Introducing Stripe Directory, a new way for you (and your agents) to search for businesses on the Stripe network.
29
29
30
245
374,996
Adrian Ziegler retweeted
The degree to which you are awed by AI is perfectly correlated with how much you use AI to code.
84
205
69
1,939
2,467,090
Adrian Ziegler retweeted
giving claude access to turbotax
13
85
5
2,832
98,810
Adrian Ziegler retweeted
The Agent axioms: 1. There is always a workflow (it may be trivial such as the implicit single step workflow) 2. Workflows may contain agents (LLMs with tools in a loop) 3. Tools are workflows ((even if trivial per 1) which can contain agents per 2)
6
3
18
4,929
Adrian Ziegler retweeted
I've spent hundreds of hours these past few months prompt engineering. Most of it is tedious trial and error, but I figured I'd share what's worked for us: leveraging markdown vs. xml, how we iterate on inputs, testing different LLMs, etc. Read more @ cloudcruise.com/blog/prompt-…!
2
3
1
9
2,076
There appears to be a massive outage going on... Twitch, Discord, Google Cloud, Google, Google Meet, Google Nest, CharacterAI, Etsy, Khan Academy, Google Drive, Google Maps, Pokemon TCG, Dialpad, Mailchimp, HighLevel, Amazon Web Services, OpenAI, Cloudflare, Anthropic, Breezeline, Dragon Ball, State Farm, Embark Studios, Gmail, Rocket League, DoorDash, Wells Fargo, Marvel, MLB TV, Google Gemini, Fortnite, Spotify, Shopify, Snapchat, Tekken, Box, Equifax, Roll20, Cursor, Looker Studio, FuboTV, IKEA, reCAPTCHA, GitLab, Steam, Clover POS Systems, AMC Theatres, NPM
217
750
413
4,257
780,293
AGI is going to be achieved by a product, not necessarily a “model”.
289
189
120
3,103
603,861
Adrian Ziegler retweeted
Replying to @nptacek
This is not the core issue. The core issue is that the LLM has to autonomously and in general way figure out that it is natively not well adapted to do this task in its head, that it doesn’t succeed in doing so, and that it should do this and that instead to solve it.
23
12
1
370
33,436
Adrian Ziegler retweeted
when you need the acquisition to go through
57
32
14
2,108
198,748
Adrian Ziegler retweeted
Plz stop making agent demos planning trips or booking flights, how many flights are you even taking??? Make them do repetitive stuff no one wants to do instead
123
90
30
2,116
173,795
Adrian Ziegler retweeted
Replying to @divya_vikash
please make it stop
58
49
39
1,031
78,926
Adrian Ziegler retweeted
legacy software companies adding an ai chatbot to their product
239
5,925
419
69,791
2,566,940
Adrian Ziegler retweeted
With @cloudcruise_app (YC W24), you can build automations that work directly in your browser. Put repetitive work on autopilot like finding sales leads, filling out admin forms, or downloading documents. ycombinator.com/launches/KbX… Congrats on the launch @VereWhit, @adrmtu & Felix!
7
4
2
58
30,001
I supect "LLMs just predict text" is a Blank Map fallacy. People know nothing else about LLM internals besides that. Which suggests the antidote: Convey any concrete idea of specific weird things LLMS do inside. So here's my story about reproducing a weird LLM result...
51
83
34
914
293,349
Adrian Ziegler retweeted
MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers abs: arxiv.org/abs/2305.07185 paper page: huggingface.co/papers/2305.0…
15
207
39
1,131
1,530,694
Today I used GPT-4 to make "Wolverine" - it gives your python scripts regenerative healing abilities! Run your scripts with it and when they crash, GPT-4 edits them and explains what went wrong. Even if you have many bugs it'll repeatedly rerun until everything is fixed
142
744
243
4,610
1,749,295
Adrian Ziegler retweeted
I'm pretty optimistic that the LLM reliability / factualness issue can be fixed. The key is to use LLMs as a dialog interface and not as a store of knowledge. LLMs as the query layer between a human user an a knowledge graph with sources (which can be hybrid generated/curated).
52
119
29
1,057
205,039