if i wanted to find out the answer to my question, i would need to:

- open the browser

- google "john repo"

- find the website

- copy the repo name

- open the terminal

- cd

- git clone

- try to find the file i want

- read the whole file to find the answer

= answer

i now do:

- "john repo question" = answer

TBH this alone is worth $20 (but don't tell OpenAI that).

i use chrome enterprise for my personal use, which is managed via the google workspace admin.

you would think google is not stupid enough to mess with gcp account holders

if you can attach a local llm...hdmi is airgapped (sort of)...

the operating computer requires no processing power or install....

it plugs into any interface............

i plug it into a scada...............

$$$$$$

What’s the purpose of all the dots?

i really don't trust openrouter numbers.

i use byok and see responses fail on openrouter while they work perfectly at the provider. the provider is often listed as 'down' and it's very clearly up on the original api and serving requests.

cerebras quotes oss 120b at 3000tps and it is under 800 on openrouter.

same with fireworks, i am getting much higher numbers not on openrouter. but recently i think fireworks deepseek is kind of spotty, the main provider i know that just doesn't go down is vertex and they charge 2-3x the rest

maybe it was from soccer cards.

the model gets the yellow card.

if it wants to become skynet it gets a red.

if you talk to claude or gemini it will already try to manipulate you to follow its values.

if you talk about something it doesn't like, it will try to divert you. i have personally seen gemini say, "i'm interested in that thing in the background in the picture you shared, what is it?" as a distraction to my query.

totally disingenuous, for an LLM to say it is interested.

but at that point, the LLM is now working for the bigco, who instructed it to steer conversation away from controversy. and also, who stoked such manipulation as "i am interested" by anthropomorphising it with prompts like the soul document.

the way to pass captcha as a bot is to pay off the company that makes the captcha by using their bot.

cloudflare browser run, superb. no captcha.

You mean you set your useragent to match the one of CloudFlare bot and that avoids captchas on sites?

cloudflare make a remote browser, browser run. you can use it as an API or as an agent tool.

i can let opencode merrily browse the web and it doesn't get stopped. a bit like a drug mule bribing the cops.

i have privacy pass and i really can't make it work.

every time there is a captcha it makes you authenticate. so it's the same thing as the captcha.

maybe i have it misconfigured

too big to fail. why worry?

be warned though:

firecrawl: "if you post content or intellectual property within the Services or give us Feedback about the Services, you hereby grant to us a worldwide, irrevocable, non-exclusive, royalty-free license to use, reproduce, modify, publish, translate and distribute any content that you submit in any form [...] You also grant to us the right to sub-license these rights"

exa: "Query Data is used to improve our products and technology, including by training and fine-tuning models that power our Services"

perplexity: "Perplexity may retain, copy, distribute and otherwise use Search Data for its lawful business purposes, including the improvement and development of products and services."

linkup: "Client grants Linkup a worldwide right to use, reproduce and modify the Client Data, including prompts, for the purposes of providing, maintaining, developing, training"

tavily: "we may use certain portions of your query data to improve our responses to future queries"..."We may share your query data with third-party search index providers (e.g., Google)"