Tyler Olson

8.1K posts

Tyler Olson banner
Tyler Olson

Tyler Olson

@TyOlson

Founder: https://t.co/4vb60KOuvT @MDRNfoundation, Away Agents, @SHYLDAcademy | Inspirational Keynote Speaker | Entrepreneur | Cybersecurity | Adventurer | Techno Lover

Minneapolis, MN Katılım Şubat 2009
3.1K Takip Edilen2.6K Takipçiler
Samuel Spitz
Samuel Spitz@samuel_spitz·
Doing a virtual launch event for Replit tomorrow We’ll be rolling out one of our most impactful releases yet Reply here for an invite
English
79
2
117
8.5K
Tyler Olson retweetledi
Aaron Levie
Aaron Levie@levie·
It’s remarkable how often you need to be dramatically upgrading your AI architecture given the pace of progress in AI models right now. If you’re building agents, you basically need to throw away large parts of previous work that you setup to compensate for model limitations every few quarters. The systems you built to mitigate context window limits aren’t useful anymore, and for many use-cases it’s easier just to throw more compute at a problem today in ways that wouldn’t have worked previously. If you’re deploying agents in a workflow, you likely need to equally be rethinking your core systems at about that same frequency. The way you would deploy agents in an enterprise 18 months ago is entirely different from the best practices that you’d have today. This is partly why everyone’s working so hard right now. Right as a best practice is solidified, models improve dramatically, and that old work is rendered obsolete. Unclear that this lets up anytime soon, which is why the it pays to be so wired in right now.
Sam Hogan 🇺🇸@samhogan

most of tooling around llms was built for a world that largely doesn’t exist anymore RAG, GraphRAG, Multi Agent Orchestration, ReAct frameworks, prompt management/versioning tools, LLMOps tooling, eval tools, gateways, finetuning libs, etc all obsoleted in in the last 3 months

English
99
106
975
243.1K
ElevenReader
ElevenReader@elevenreader·
Announcing the Audiobooks Creator Challenge. Create. Publish. Win. Win AirPods Max & credits to publish your full book.
English
831
69
336
96.2K
Rork
Rork@rork·
Reply if you: • You have 1K+ followers on X • Ready to share honest feedback about Rork Max We'll give you early access + 1 month free Pro plan
English
206
11
205
14.8K
Tyler Olson
Tyler Olson@TyOlson·
Bought DollarSaasClub.com yesterday, to help fuel the democratization of software :) Coming soon: almost any software you want for $1/mo each. Builders: Want to join me in this new adventure?
English
4
1
10
231
Samuel Spitz
Samuel Spitz@samuel_spitz·
I have a mind blowing new product at Replit that I’m going to give out to a few startups early. Trust me, even if you don’t use Replit, you’ll find this super helpful. Who wants in?
English
40
0
67
6.8K
Ben Lang
Ben Lang@benln·
What are you building this weekend? Share links, curious to see.
English
621
7
434
59.9K
Tyler Olson retweetledi
Aakash Gupta
Aakash Gupta@aakashgupta·
This is a dopamine loop, and it’s one of the most powerful ones humans have ever encountered. Every time you prompt an AI and get a useful result back in seconds, your brain gets a hit. Variable-ratio reinforcement, same mechanism as slot machines, except the reward is real: actual output, actual progress, actual leverage on your ideas. Traditional work follows a delayed-reward structure. You write code for 6 hours, maybe it compiles, maybe you get feedback in a week. The gap between effort and reward is wide enough that motivation decays constantly. AI compresses that loop to seconds. Effort → reward → effort → reward. Your prefrontal cortex stays engaged because the next payoff is always one prompt away. This is why people describe it as “fun” when they’re actually working 14-hour days. The subjective experience of effort disappears when reward frequency is high enough. The “harder than ever” part is real too. When your bottleneck shifts from execution to imagination, you run out of excuses to stop. There’s no “waiting on the build” or “blocked by review.” Every idea you have can be tested immediately, which means your brain never gets a natural stopping point. People who thrive on this are selecting for a specific neurotype: high novelty-seeking, high conscientiousness, tolerance for rapid context-switching. That’s maybe 10-15% of the population. The other 85% will experience the same tools as overwhelming, not energizing. And that split is going to define the next decade of who captures value from AI and who gets displaced by it.
Nat Eliason@nateliason

Nearly every ambitious person I know who has dived into AI is working harder than ever, and longer hours than ever. Fascinating dynamic tbh. I have NEVER worked this hard, nor had this much fun with work.

English
204
482
4.5K
565.6K
Tyler Olson
Tyler Olson@TyOlson·
@ReplitSupport I want to have multiple devs working on the same app. Should we use replit projects (I see this is being changed in Mar?) or git tab branches? I'm noticing many differences between them. Pros/cons of each?
English
1
0
0
37
Tyler Olson
Tyler Olson@TyOlson·
@mattyp I want to have multiple devs working on the same app. Should we use replit projects (I see this is being changed in Mar?) or git tab branches? I'm noticing many differences between them. Pros/cons of each?
English
0
0
0
30
dharmesh
dharmesh@dharmesh·
I'm fully supportive of @karpathy's bringing back RSS/Atom feeds (which candidly, I don't think we should have lost in the first place). In a way, RSS was useful because it was a super-simple protocol/standard for content consumption. As a weekend project, I'm considering building something I've had on the back-burner for a while. It's called OneFeed (yes, I own OneFeed .com). The idea is to have an agent that unifies RSS (and possibly other sources) and be able to run an LLM on the feed items for filtering, prioritizing -- and taking action. This is an idea that many of pursued before (and maybe some still are). But, with reasoning LLMs now, I think something more interesting can be done. It's a bit like BYOA (Bring Your Own Algorithm), instead of being at the mercy of someone else's.
Andrej Karpathy@karpathy

Finding myself going back to RSS/Atom feeds a lot more recently. There's a lot more higher quality longform and a lot less slop intended to provoke. Any product that happens to look a bit different today but that has fundamentally the same incentive structures will eventually converge to the same black hole at the center of gravity well. We should bring back RSS - it's open, pervasive, hackable. Download a client, e.g. NetNewsWire (or vibe code one) Cold start: example of getting off the ground, here is a list of 92 RSS feeds of blogs that were most popular on HN in 2025: gist.github.com/emschwartz/e6d… Works great and you will lose a lot fewer brain cells. I don't know, something has to change.

English
58
25
333
52.4K
Tyler Olson
Tyler Olson@TyOlson·
@Faytuks I value receiving reliably accurate, interesting, and timely global updates from you.
English
0
0
1
108
Faytuks News
Faytuks News@Faytuks·
Before the weekend I'd like to say thank you to all my followers. Your engagement, comments and opinions is what make this account truely enjoyable. If you have any complaints/opinions on the account feel free to share. Thank you in advance!☺️
English
36
3
452
31K
Tyler Olson
Tyler Olson@TyOlson·
@pirroh I'm building software with replit to help organization leaders align and scale teams. Username: TylerMOlson
English
0
0
0
33
Michele Catasta
Michele Catasta@pirroh·
I’m feeling jolly. Let me be your not-so-secret Santa 🎅🏻 Reply to this post with an idea you want to create, and your Replit username. Tomorrow I’ll send $50 in credits to the first 100 replies.
English
124
18
155
35.1K