Jonathan Archer (@apewithllm) header
Jonathan Archer (@apewithllm) profile picture

Co-founder of @Openllmsh

Joined October 2026
Photo by Jonathan Archer (@apewithllm)Photo by Jonathan Archer (@apewithllm)Photo by Jonathan Archer (@apewithllm)Photo by Jonathan Archer (@apewithllm)Photo by Jonathan Archer (@apewithllm)Photo by Jonathan Archer (@apewithllm)Photo by Jonathan Archer (@apewithllm)Photo by Jonathan Archer (@apewithllm)Photo by Jonathan Archer (@apewithllm)Photo by Jonathan Archer (@apewithllm)
USE YOUR AI SUBSCRIPTIONS, LOCAL INFERENCE, API KEYS - WHEREVER YOU WANT @OpenLLMsh
4
5
19
798
Sonnet 5.5 intelligence that can be run locally 👀
Inkling 2 Mini is a looped transformer that runs on a laptop. Looping lets a model think more and write less. At this scale, its thought process remains monitorable; this may not stay the case. We’re also sharing a variable-loop research model to enable further study.
25
I see Gemini benchmark maxxin, but has anyone started using it again?
28
Jonathan Archer retweeted
Deception needs a motive, and a motive needs a soul
636
2,333
738
11,448
4,269,634
When I ask my agents for good angels to invest into OpenLLM is suggests people like @garrytan, @justinkan, @naval and more Should be easy right?
31
Today is not the day to do a product announcement. It's GTA 6 day
1
3
67
Don't be like Lou, get a couple subs a put them together in @OpenLLMsh
It cost me ~$4,000 to build MailCheap with Opus 5.5 on @cursor_ai so ironically, it's my first unprofitable product.
1
1
44
Jonathan Archer retweeted
if you're feeling a little uneasy about the grounding of all US planes remember to spend as much time on your phone as possible. the more information you ingest as you scroll the calmer you will become
174
2,128
93
42,671
848,549
Wow - Grok Bot is running on some pretty serious hardware CPU 8 vCPU RAM 15 GiB Disk 128 GB SpaceX team isn't cheaping out
35
did someone say inference sandbox?
18
Jonathan Archer retweeted
There is no substitute for the person who Knows What To Do.
1,316
4,856
482
41,392
3,003,273
it feels like to use codex inside of claude code
1
50
Jensen Huang doc out tomorrow... how are they so fast?
🤖 Made with AI
68
DeepChat 今天发布了 v1.1.4,OpenLLM 现在是内置服务商了。 你的 Claude、ChatGPT、Kimi、Grok 订阅、API Key 和本地模型,都可以直接在 DeepChat 里用。在服务商设置里打开 OpenLLM 就行。 感谢 @imwritingbugs 合并这个 PR
1
4
660
CODEX RESET COMING THURSDAY
3
3
108
Do you want a model to pick models for you?
2
37
"You have 6 paying users today, all on Pro at $30 a month, which comes to $210 a month." a quote from my @bot don't let them do your accounting
1
1
25
Are there any hardcore builders using Muse? I feel like everyone is either using Hermes or Grok Bot rn
1
2
29