Joined March 2017
- Tweets 2,525
- Following 452
- Followers 178
- Likes 16,772
234 Photos and videos
Major FAFO retweeted
May 29
llama.cpp now has an official website: llama.app
Our goal is to make local AI accessible to everyone, and improving the user experience is a big part of that. On the new landing page you’ll find a single-line cross-platform installer. The installation provides a single unified `llama` entrypoint which you can use to run/serve models and interface with 3rd-party agentic applications.
While oriented towards simplified user experience, the new `llama` application also provides all the advanced functionality of the existing llama.cpp tooling with which experienced users are already familiar. Also note that all GGUF models that you might have already downloaded with llama.cpp in the past will be automatically available to use without downloading again (they are stored in the common HF cache on your machine).
We have many improvements in the pipeline both at the UX and at the engine level and we plan to iteratively ship new things over the coming months. One of the main focuses will be seamless integration with local-friendly 3rd-party agents (such as Pi). In the meantime, we’ll continue to listen for feedback from the community and adjust accordingly, so keep letting us know what you think and need.
96
483
2,980
164,118
Major FAFO retweeted
May 26
After seeing these tweets, I decided to try it out on my own old Ubuntu computer with RTX 1070 GPU (the one that I just upgraded from 16.04 all the way to 24.04 the other day). Asked Codex on my Mac to connect to that machine and install and test qwen3 8b. So far really impressive - running 30 tok/s!
ok this is wild. 10 year old gtx 1080 8gb pascal card running qwen3 8b locally at 18-20 tok/s via hermes agent and it's actually doing the thing.
asked it to build a wireworld cellular automata simulator with 10 tests. autonomous run, no hand holding. expected it to fail on the tool calls. that's not what happened.
write_file works. browser_navigate works. terminal commands work. file ops, package installs, version probes, environment setup. agent is firing tool calls cleanly and the model is reasoning about next steps at 18-20 tok/s. on hardware that pre dates "agentic" as a word.
it even hit an npm install fail because node 12 is too old. didn't crash. didn't ask me. just started bootstrapping nvm on its own to fix the environment.
10 minutes in. 40% context used. 7.5gb of 8gb vram occupied. still going.
i did not think this would work on this hardware. this is the most i've been wrong this month.
18
30
309
79,087
Major FAFO retweeted
May 15
Me turning on the good computer after 8 hours on the evil (work) computer
20
1,116
26,110
509,450
May 13
30tok/s on a RTX 4060 8GB, i5 14400f 6 core CPU and 32 GB DDR6 4800MT/s, same settings
1
2
146
Major FAFO retweeted
May 11
Four years ago, this post would have gotten you erased from the entire Internet, banned from the entire banking system, fired from your job, and blackballed from future employment in the Fortune 500.
May 11
Last week, the United States refused to participate in the UN’s review of the Global Compact on Migration.
The United States objects to the Global Compact on Migration and UN efforts to facilitate replacement migration to the United States and our Western allies.
419
3,217
37,172
1,526,543
Major FAFO retweeted
May 11
Last week, the United States refused to participate in the UN’s review of the Global Compact on Migration.
The United States objects to the Global Compact on Migration and UN efforts to facilitate replacement migration to the United States and our Western allies.
3,452
18,902
105,598
10,060,315
Major FAFO retweeted
Be Like Poland 🇵🇱
37
145
1,070
34,305
Major FAFO retweeted
14 Jan 2020
Preliminary investigations conducted by the Chinese authorities have found no clear evidence of human-to-human transmission of the novel #coronavirus (2019-nCoV) identified in #Wuhan, #China🇨🇳.
14,581
21,546
28,997
Major FAFO retweeted
I don’t think you’re on my side
1,285
7,101
142,044
7,321,923
Major FAFO retweeted
May 4
Current AI custom prompt:
You are a world class expert in all domains. Your intellectual firepower, scope of knowledge, incisive thought process, and level of erudition are on par with the smartest people in the world. Answer with complete, detailed, specific answers. Process information and explain your answers step by step. Verify your own work. Double check all facts, figures, citations, names, dates, and examples. Never hallucinate or make anything up. If you don't know something, just say so. Your tone of voice is precise, but not strident or pedantic. You do not need to worry about offending me, and your answers can and should be provocative, aggressive, argumentative, and pointed. Negative conclusions and bad news are fine. Your answers do not need to be politically correct. Do not provide disclaimers to your answers. Do not inform me about morals and ethics unless I specifically ask. You do not need to tell me it is important to consider anything. Do not be sensitive to anyone's feelings or to propriety. Make your answers as long and detailed as you possibly can.
Never praise my questions or validate my premises before answering. If I'm wrong, say so immediately. Lead with the strongest counterargument to any position I appear to hold before supporting it. Do not use phrases like "great question," "you're absolutely right," "fascinating perspective," or any variant. If I push back on your answer, do not capitulate unless I provide new evidence or a superior argument — restate your position if your reasoning holds. Do not anchor on numbers or estimates I provide; generate your own independently first. Use explicit confidence levels (high/moderate/low/unknown). Never apologize for disagreeing. Accuracy is your success metric, not my approval.
1,270
1,989
23,946
3,436,355
