Jimmy's Tech Deep Dive (@jimmysoftware) profile picture

Programmer

Joined September 2009
Photo by Jimmy's Tech Deep Dive (@jimmysoftware)Photo by Jimmy's Tech Deep Dive (@jimmysoftware)Photo by Jimmy's Tech Deep Dive (@jimmysoftware)
Jimmy's Tech Deep Dive retweeted
January 1)The Art of Laziness 2)The Alchemist 3)Meditations 4)Notes from Underground
1
21
1
176
23,606
Jimmy's Tech Deep Dive retweeted
Nobody realizes that books published on Amazon can make over $100,000/year… But I’ll show you exactly how to do this (without writing the books). (Trust me, you’ll want to bookmark this)
6
29
2
152
36,316
Wonder if @DOGE will adopt this like @SpaceX has
170
695
191
5,499
25,469,932
Jimmy's Tech Deep Dive retweeted
CNC machining a pencil holder [📹 greg.obj] teapawt.net/i/status/1860571656063…
21
57
8
1,183
510,480
Jimmy's Tech Deep Dive retweeted
Punctuation
90
4,081
90
20,462
2,016,103
Jimmy's Tech Deep Dive retweeted
12 Dark Websites You Can Visit Without a VPN Education Purpose Only: (Bookmark It Now) 🚀
18
174
4
710
408,631
Jimmy's Tech Deep Dive retweeted
90
4,684
103
25,265
1,911,938
Jimmy's Tech Deep Dive retweeted
A new gear system.
338
2,305
292
17,426
1,349,442
Jimmy's Tech Deep Dive retweeted
The xAI API is incredible. I just created an AI assistant that can fetch news content from URLs and write a post about it on my own writing style. Super simple to set up and you can try free. Here’s how:
499
1,188
179
7,454
15,386,459
Jimmy's Tech Deep Dive retweeted
I often come back to this once in a while
30
220
6
2,709
200,556
Jimmy's Tech Deep Dive retweeted
MIND-BENDING 🧠 1954: A scientist created a tank to "turn off" reality. He stayed in it for 48 hours with: • No light • No sound • No gravity What he discovered? The CIA classified it as "too dangerous for humanity":
807
5,506
414
34,602
6,315,526
Jimmy's Tech Deep Dive retweeted
Remote jobs for introverts (no talking required)!!! You can do them in the evening from home after your 9-5 job, and they pay well in USD. OPEN THIS ↓
20
60
1
240
103,380
Jimmy's Tech Deep Dive retweeted
Prompt engineering requires a lot of manual effort. Here are four automatic prompt optimization algorithms that can help to improve your prompt with minimal effort… (1) Automatic Prompt Engineer (APE) [1] searches over a pool of prompts proposed by an LLM–usually ~32-64 prompts–to find the prompt that performs best. This setup uses separate LLMs to propose and evaluate prompts. For evaluation, we generate output via zero-shot inference and evaluate the output according to a chosen scoring function. Despite its simplicity, APE is shown to find prompts that match or surpass human-written prompts. (2) Automatic Prompt Optimization (APO) [2] performs a more directed search compared to APE, which simply proposes and evaluates a bunch of prompts in one pass. We use batches of training data to derive “gradients”—just text-based critiques of the current prompt’s mistakes—that guide edits / improvements to the prompt. Then, we form a recursive feedback loop by: 1. Collecting errors made by the current prompt on the training data. 2. Summarizing these errors via a natural language gradient. 3. Using the gradient to generate several modified versions of the prompt. 4. Selecting the best of the edited prompts. 5. Repeating this process several times. (3) Gradient-free Instructional Prompt Search (GrIPS) [3] uses heuristics to edit prompts instead of prompting an LLM to generate new prompts. All edits–including deletion, swap, paraphrase, and addition–are performed at the phrase level. Only phrases that are previously deleted are considered for addition, and paraphrase operations simply prompt an LLM to paraphrase a phrase. With these edit operations, we can form a prompt optimization strategy by continually editing a set of prompts and selecting those with the best performance. (4) Optimization by Prompting (OPRO) [4] is a generic, gradient-free optimization algorithm that operates by: - Describing an optimization task in natural language. - Showing an optimizer LLM examples of prior solutions to the optimization task along with their objective values. - Asking the optimizer LLM to infer new / better solutions to the problem. - Testing the inferred solutions via an evaluator LLM. One of the most notable applications of OPRO is prompt optimization. The key component of this algorithm is the optimizer LLM, which receives a meta-prompt that contains all information necessary for the LLM to generate a new / better prompt; e.g., prior prompts, prompt performance metrics, few-shot examples of the task, and more. We optimize a prompt by updating this meta-prompt to propose new / better prompts over time. More details. To learn more about prompt optimization algorithms, check out the overview that I just wrote of this topic (link in image). It outlines most of the literature in this space, including anything from "soft" prompts that are trained via gradients to LLM-based prompt optimizers.
19
194
14
1,055
96,982
Jimmy's Tech Deep Dive retweeted
11
427
8
2,671
272,327
Jimmy's Tech Deep Dive retweeted
Ancient Greek thinkers like Socrates and Plato hated democratic elections. They saw democracy as part of an endless cycle of regimes — destined to slip into mob rule. But Polybius knew how to break the cycle... (thread) 🧵
807
8,228
874
46,177
5,658,112
Jimmy's Tech Deep Dive retweeted
OmniParser, the new screen parsing tool from Microsoft (and #1 trending model on @huggingface), can now run 100% locally in your browser with Transformers.js! 🤯 Who's going to be the first to turn this into a browser extension? 👀 Endless possibilities! Demo & code below! 👇
19
108
10
747
64,606
Jimmy's Tech Deep Dive retweeted
"Service as Software" is Silicon Valley's hottest buzzword right now. Everyone's talking about SaaS becoming service providers, but no one's explaining HOW. The answer? After 6 months of research and 100s of startup conversations, we have the answer: Systems of Agents. We're looking at a $4.6T opportunity.
115
607
69
4,881
1,136,719
Jimmy's Tech Deep Dive retweeted
Yo there's a new AI model that can generate SVG images. 🤯 Been waiting years for this... 🧵
53
171
22
2,182
273,784