andy nelson

216 posts

andy nelson banner
andy nelson

andy nelson

@Andy_Nelson82

God bless Texas

Fort Worth, TX Katılım Kasım 2015
223 Takip Edilen65 Takipçiler
andy nelson
andy nelson@Andy_Nelson82·
@techdevnotes They may just use the composer models and call it a group project
English
0
0
2
554
Tech Dev Notes
Tech Dev Notes@techdevnotes·
June is ending, are we even expecting any big Grok model update or feature this month ...
English
34
2
186
11.4K
chy_derah
chy_derah@TheKingDaughtaa·
Why is this so funny😂?
English
598
3.3K
48.1K
5.9M
andy nelson
andy nelson@Andy_Nelson82·
@techdevnotes I'll take the new cursor SOTA model till the new grok model drops.
English
0
0
0
323
andy nelson
andy nelson@Andy_Nelson82·
@tonbistudio I'm enjoying your videos, appreciate the level of detail.
English
0
0
0
23
tonbi
tonbi@tonbistudio·
Put together a playlist for my Hermes Agent Masterclass videos. Four down, 6 to go! This week's will be on models, especially local models! (everyone's favorite topic) youtube.com/playlist?list=…
English
2
6
73
30.9K
Aether Oracle
Aether Oracle@aether_oracle·
@skcd42 Do we sign in with our Cursor subscription or is this also through the Grok subscription and usage? (Also, very excited for this merger)
English
2
0
5
644
skcd
skcd@skcd42·
We are excited for all of you to try out Composer 2.5 in Grok Build starting today! To use composer-2-5 do `/model` in Grok Build and type in Composer to switch Composer 2.5 comes with 200k context window and supports: subagents, MCPs, skills and additionally also works with your .cursor settings
English
69
47
649
39.3K
andy nelson
andy nelson@Andy_Nelson82·
@mrfundman It's tough but I would guess m3p is almost as good as the S but cheaper to insure and maintain. Less parts and less things to go wrong over the life of the car.
English
0
0
0
270
mr fundman
mr fundman@mrfundman·
Please help my friend decide, this is a very serious question, used 2023 S Plaid for 64k or new M3P for 55k?
mr fundman tweet media
English
532
15
522
165.8K
andy nelson
andy nelson@Andy_Nelson82·
@chribjel I love groks non-api pricing but holy crap they need new tech yesterday.
English
0
0
1
63
Christoffer Bjelke
Christoffer Bjelke@chribjel·
insane cost inefficiency from grok build 0.1 costs the same as gpt-5.5 xhigh, but performs like shit the next grok build model can't come soon enough DeepSWE benchmark
Christoffer Bjelke tweet media
English
35
3
277
21.6K
The Internet Fish
The Internet Fish@TheInternetFish·
Nice to see a real DJ and not just someone that stands behind a big piece of equipment and presses buttons
English
82
396
4.5K
238.9K
andy nelson
andy nelson@Andy_Nelson82·
@uzairansar I did. You use /agy command. Buts it slow and doesn't chain comms
English
0
0
0
32
Uzi
Uzi@uzairansar·
Has anyone figure out how to add Antigravity CLI as a model provider or a skill in Hermes?
Uzi tweet media
English
8
0
31
7K
Hermes Agent Tips
Hermes Agent Tips@HermesAgentTips·
where do you currently run Hermes Agent on? - Windows native (beta) - MacOS - Linux - Windows (WLSL2)
English
95
0
43
9.5K
andy nelson
andy nelson@Andy_Nelson82·
@DanKulkov Cursor needs to drop Kimi, it's a crappy benchmaxxed model and a bad foundation
English
1
0
0
3.5K
movie tweets
movie tweets@lauren_w67·
Dude signature under duress would not be over looked that fast
English
89
256
15.4K
258.4K
andy nelson
andy nelson@Andy_Nelson82·
@skcd42 i literally just upgrade to 0.2.2, ya'll are shippin' fast
English
2
1
6
1.1K
skcd
skcd@skcd42·
Bug fixes shipping to Grok Build 0.2.3 (release notes will be available in the TUI) - add “Yes, and don't ask again for anything (always-approve mode)" - add alpha/stable to welcome screen - JetBrains/JediTerm terminal detection so TUI does not get confused and detect it as some other terminal - persist model ID instead of display name for default_model - clamp Q&A height to prevent ratatui buffer overflow - better UX for tmux inside ssh copy-paste issues - store vim mode persistently in the config.toml to prevent restart loss - memory usage improvements for managing chat history on the hot path
English
351
988
2.8K
1.7M
David Hendrickson
David Hendrickson@TeksEdge·
📊 LLM Stats leaderboard has been updated with its latest model, Google 3.5 Flash. It comes in at #6. This leaderboard takes into account more than just individual benchmarks or throughput performance.
David Hendrickson tweet media
English
4
1
22
4.4K
andy nelson
andy nelson@Andy_Nelson82·
Grok 4.3 really showing its age more and more sadly. The new agentic first models really shine on tool calling vs the legacy models.
English
0
0
1
50
️️️️ ️ᅠ‏️️️️ ️ᅠ️️️️ ️️️️️ ️ᅠ
Grok Community member Jayden Davis stated that after a mere 5 prompts, he has used 21% of his Monthly free Grok Build credits as a regular SuperGrok user. To get the most out of build you are really going to want to take advantage of the $99/mo for 6 months promo offer if it is still available.
️️️️ ️ᅠ‏️️️️ ️ᅠ️️️️ ️️️️️ ️ᅠ tweet media
English
16
2
44
4.8K
andy nelson
andy nelson@Andy_Nelson82·
@spyced 3.5 flash seems like a big improvement in real world work IMO
English
0
0
1
81
Jonathan Ellis
Jonathan Ellis@spyced·
I definitely get the Flash 3.5 hate (wtf 3x more expensive) and that was also my first reaction, but when we tried replacing Flash 3-preview with 3.5 in SlopCop it was both 4x faster (expected) and 2x cheaper (very unexpected) -- it's just that much better at agentic work. Working on a writeup for next week.
English
17
11
288
25K
andy nelson
andy nelson@Andy_Nelson82·
@gabor 3.5flash seems to handle tooling with much more grace. great for agentic work.
English
0
0
0
95
Gabor Cselle
Gabor Cselle@gabor·
So far my main takeaway from my AI-maxxing day is that Gemini 3.5 Flash is very fast.
English
8
0
52
5.3K