Herr Gromov (@yougrom) header
Herr Gromov (@yougrom) profile picture

https://teapawt.org/t.co/XCkyXlYLMx…

Berlin
Joined September 2011
Photo by Herr Gromov (@yougrom)Photo by Herr Gromov (@yougrom)Photo by Herr Gromov (@yougrom)Photo by Herr Gromov (@yougrom)Photo by Herr Gromov (@yougrom)Photo by Herr Gromov (@yougrom)Photo by Herr Gromov (@yougrom)Photo by Herr Gromov (@yougrom)Photo by Herr Gromov (@yougrom)Photo by Herr Gromov (@yougrom)
Herr Gromov retweeted
We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.
1,711
6,772
1,587
56,891
8,247,773
Herr Gromov retweeted
Andrej Karpathy just dropped his first course since joining Anthropic. 90 free minutes to become an AI engineer before 2027: 19:13 - Getting Hired Without a Degree 30:31 - How Claude Actually Works 52:13 - Your First AI Agent Bootcamps charge $20,000 to teach less than this. You probably don't have 90 minutes right now. Don't lose this in the feed. Watch it tonight. Then read the guide below and build your first loop.
3
12
1
69
14,625
CS50: Основи програмування для бізнес-професіоналів Harvard University in @PrometheusMOOC
1
42
CSS Specificity Wars #CSS
32
⚡ Flexbox Froggy Pro ➡ A game for mastering CSS flexbox with infinite practice levels ➡ flexboxfroggy.com/ #css #flexbox
16
⚡Як працюють браузери ➡ web.dev/howbrowserswork/
15
⚡Поради та рекомендації високого рівня написання розумного, керованого, масштабованого CSS ➡ cssguidelin.es/ ➡ codeguide.co/ #css
18
EOS Radio - Noizar January 2023 by Noizar ift.tt/4R2kGqF
23
ASA 808 FluxFM Clubsandwich Mix by ASA 808 ift.tt/fEAS3ta
LuniZ - I Got 5 On !t (Benedikt Frey Rework) by benedikt frey ift.tt/3pgTpCI
VESELKA PODCAST 022 | Sergen Makaren by VESELKA ift.tt/3uUk3me