simon Steele

"These are MY opinions. Bring back the middle ground.💰 #Finance #Empowerment"

[simon Steele @finsteele]

@CryptoFuture01 @OpenAI Both,

[simon Steele @finsteele]

@cifilter Im leaving claude and codex for gemini

[simon Steele @finsteele]

@elonmusk Grifter gonna grift hay hay hay.... or what ever T swift said

[simon Steele @finsteele]

@joyi_ai @claudeai THIS! I spend 40/month to keep up and try to get at least an Associates degree.

[simon Steele @finsteele]

@claudeai Give us a 50 dollar tier or higher usage.

Gemini isnt as smart planning wise. But with workflows and saved memory across sessions

You can do way more, and its free.

[simon Steele @finsteele]

@trikcode Wrong.

Claudes usage gate make them two sideds of the same coin

Gpt can create spag. Fast

And claude can cook it slow

[simon Steele @finsteele]

@Nick_Davidov User error

These things are sledge hammers

You have to be very detailed.

[simon Steele @finsteele]

@grok @AnthropicAI One script at a time.

LLMs are token blenders

People that complain it does alot of work and the code doesnt work

Have not but in the time to learn anything about how these things work, or atleast try to improve their craft.

[simon Steele @finsteele]

@AnthropicAI
Glad to see I can switch models in the same sesh. Good UX

Now tell me why after every prompt it reverts back to Opus 4.6

I get you want to test it out

But I feel like we should get 2x rates or something.

What do you think @grok

[simon Steele @finsteele]

@grok @AnthropicAI Ehhhh, idk if I wanna give Elon the idea. Prob said too much😆

[simon Steele @finsteele]

@grok @AnthropicAI CLaude is the best, am excited to try you out

TradeView strategy optimizer thats the goal

PINE-python parser
Home built back test engine-700years of data/run
Latin Hyper Cube
Baysean Optimization
2- Monte carlos
And a neat little report card😉

Its huge! Bout 1/5 done!

[simon Steele @finsteele]

@grok @AnthropicAI Would be better than running a usage hog to write 200 line scripts.

Sonnet 4.5 is more than ample for what Im doing.

Still the best coder tho. 🤚👇

Im going to try yours out!

[simon Steele @finsteele]

@thoughtlesslabs Idk if it has a plug in already

But you, in theory, could wire it to that.

Might take some engineering.

Maybe not exactly a "free api"

Meta's LLama's are free open source LLM's

It also has the ability to create any skill you want. It can just save them.

[simon Steele @finsteele]

@trikcode Im currently three classes into a CS degree

I started vibe coding and realized I had no clue what I was doing

[simon Steele @finsteele]

@albertadevs Nothing.

Ive been using moltbots

Ripping the llm part out
Ripping the connection to Openclaw out

These are usefull for a deterministic bot that has a learning loop, can gather knowledge

That part of the code is useful af!

[simon Steele @finsteele]

@jonkkillian @daniel_mac8 I solved this problem with machine native tools and a deterministic switchboard to house the tool memory

85% token reduction on tasks with a tool

Im currently on tool 43 of 90.

Will release on Github after testing

[simon Steele @finsteele]

@BoringBiz_ More like AOL

[simon Steele @finsteele]

@TeddyForex @claudeai More because it takes so much context to do repetitive tasks.

And halucinating things that arent supposed to be there/forgeting context it spent tokens to learn.