Jeroen Dee

1.9K posts

Jeroen Dee

Jeroen Dee

@jeroendee

Proud husband and father | Ai Shepherd @ Ahold Delhaize | Ai Driven Development advocate | love Go | some martial arts | Amsterdam

Amsterdam, North Holland NL Katılım Şubat 2009
1.2K Takip Edilen181 Takipçiler
Virtual Mage
Virtual Mage@virtualmage17·
Desert Strike (Mega Drive) 🚁🔥 One of the most addictive helicopter games ever made… Classic… or overrated? 👀
English
154
157
2.6K
134.5K
blue
blue@bluewmist·
People who exercise even when they don't feel like it, what's your trick?
English
2.5K
148
5.6K
1.3M
Jeroen Dee
Jeroen Dee@jeroendee·
@KSimback Where do you get the GLM tokens from? I’ve been using Ollama cloud but it has been very slow.
English
0
0
0
54
Kevin Simback 🍷
Kevin Simback 🍷@KSimback·
I’m currently using GLM-5.1 for my agents primary model and it’s been quite good since leaving Opus Curious to get thoughts from anyone who has compared vs Minimax
MiniMax (official)@MiniMax_AI

Capable agents are the result of co-evolution between models and harnesses. We've been working with @NousResearch to ensure that M2.7 x Hermes Agent provides a top-tier experience for users. Hermes’s self-improving loop brings out the best in M2.7 through real usage. We are also launching MaxHermes, a cloud-hosted and managed version of Hermes in @MiniMaxAgent (No terminal setup, no config) If you’re already running Hermes locally, you can now give you agent a partner in the cloud with MaxHermes. The path to AGI is shorter with good company. @NousResearch 🤝 @MiniMax_AI

English
46
2
94
18.1K
Jeroen Dee
Jeroen Dee@jeroendee·
and "Announcing ... bla bla" posts.
English
0
0
0
4
Jeroen Dee
Jeroen Dee@jeroendee·
Getting sick and tired of the "introducing .... bla bla" posts.
English
1
0
0
15
Ayushi☄️
Ayushi☄️@iyoushetwt·
What's one software you use every day and still can't believe it's free?
Ayushi☄️ tweet media
English
47
3
62
17.1K
Ramin Nasibov
Ramin Nasibov@RaminNasibov·
What would you call this?
Ramin Nasibov tweet media
English
2.9K
177
1.9K
573K
Simon Willison
Simon Willison@simonw·
Shocking result on my pelican benchmark this morning, I got a better pelican from a 21GB local Qwen3.6-35B-A3B running on my laptop than I did from the new Opus 4.7! Qwen on the left, Opus on the right
Simon Willison tweet mediaSimon Willison tweet media
English
156
143
2.3K
189.5K
Jeroen Dee
Jeroen Dee@jeroendee·
@sqs Age of bespoke software @sqs Focussed personal software. Only features you truly need. I don't need a gazillion features.
English
0
0
1
89
Quinn Slack
Quinn Slack@sqs·
I just replaced 90% of my use of a hosted software subscription we use with something I built in 20min with 3 prompts. I get to cheat: I only need to rebuild the 5% of the feature set I need. I don’t care about auth or multi-tenancy or change tracking because it’s just for me. You gotta admit that this limits their pricing power when it comes up for renewal.
English
12
1
97
9.1K
Jeroen Dee
Jeroen Dee@jeroendee·
@bcherny Would be lovely if we could use the Claude sub. in another agent harness. I really like Pi.
English
0
0
0
1.5K
Boris Cherny
Boris Cherny@bcherny·
Opus 4.7 feels more intelligent, agentic, and precise than 4.6. It took a few days for me to learn how to work with it effectively, to fully take advantage of its new capabilities. Will post a few more tips throughout the day, starting with this blog post: claude.com/blog/best-prac…
English
248
552
6K
577.4K
Ado
Ado@adocomplete·
Claude Opus 4.7 is here! It handles long-running tasks better and follows instructions more precisely while requiring less supervision. It sees images at more than 3 times the resolution and produces higher-quality outputs as a result. Get it now wherever you get your Claude.
Ado tweet media
English
13
4
66
4.3K
Adrien Grondin
Adrien Grondin@adrgrondin·
Google's Gemma 4 26B A4B running on MacBook Pro M5 Max 100% native Swift Achieving over 100tk/s with Apple MLX framework
English
118
137
3.4K
343.6K
Jeroen Dee retweetledi
Mischa Sigtermans
Mischa Sigtermans@mischamartijn·
Yesterday Tesla owed me €6.400. Today they owe thousands of us. One post. 1.250+ owners. €3.8M+ in estimated FSD payments. All in 24 hours. It started in the Netherlands. Now HW3 owners across Europe are signing up. We paid for Full Self-Driving. Tesla quietly abandoned the hardware it runs on. Millions of cars. No communication whatsoever. Friends asking if I realize who I'm up against. I do. So does everyone who stopped waiting. Join hw3claim.nl if you paid for FSD.
Mischa Sigtermans tweet media
English
66
175
1K
97K
Jeroen Dee
Jeroen Dee@jeroendee·
@badlogicgames > "It also shows us that a ton of people are happy to use buggy software." What does this mean for the industry? People are in awe still of the magical stuff, and simply tolerate less quality. I wonder what people's stance would be if this were a doc editor.
English
1
0
1
539
Shopify Engineering
Shopify Engineering@ShopifyEng·
Since we open-sourced pi-autoresearch, @Shopify teams have been running it on everything. Results so far: Unit tests: 300x faster React component mounting: 20% faster CI build time: 65% reduction Made pnpm run faster Autoresearch never stops trying things you'd never have time to try. Repo: github.com/davebcn87/pi-a…
English
27
196
2.3K
311.2K
Jeroen Dee retweetledi
David Crawshaw
David Crawshaw@davidcrawshaw·
Top secret* new exe.dev feature. * I forgot to tweet about it last week.
English
0
4
26
2K
dax
dax@thdxr·
a million posts on my feed telling me how to build agents zero people talking about building agents
English
123
26
1.2K
60.1K
Shayan
Shayan@0xShayan·
Is anyone using Hermes via the GLM 5.1 Pro/Max plan and if so, how is your experience? Tagging @Teknium for vis
English
77
1
79
14.3K