ThreadTension

@l43539 @mrfarnhigh @cjzafir If you're trying to build something usually you want AI to create a spec sheet for whatever you want to achieve before building, think of it as a thorough plan.

@threadtension @mrfarnhigh @cjzafir And what does this mean in ai

After burning 400M tokens: Using deepseek v4 models without <specs> is a crime, waste of tokens, and insanity!!!

@jbhuang0604 Deepseek v4 flash is possibly the best value for money right now, pro can burn through credits though I find.

Keep getting rate-limited by Claude, so I tried out DeepSeek V4 for the first time. After 10M+ tokens, holy crap the cost is ... 🤯

@mrfarnhigh @cjzafir Specifications.

@cjzafir What’re specs?

@GoogleAIStudio Still improving and updating aipedia.wiki - The wiki for ai tools!

What are you vibe coding this weekend?

@RoundtableSpace Continuing to improve aipedia.wiki | The wiki for ai tools & news

WHAT ARE YOU BUILDING TODAY?

@heyblake Check out aipedia.wiki - a wiki for ai tools!

Drop your project URL Let’s drive some traffic

@_ivan1981_ @zUnEm01 Nice one, it's so good man!

@threadtension @zUnEm01 I’m doing the same with Gemini 2.5 Flash and it works good too 👍 Hermes is amazing

GLM 5 could be better but it is very unreliable asf! Kimi k2.6 could be better but it just has issues with understanding and following instructions, it over does stuffs and destroys my repo. Deepseek is a winner here because it understands and follows instructions with 1m context it's a plus for me. The only problem with Deepseek is this: it doesn't have vision.

@sickdotdev Imagine if it was good enough to not need be sworn at? Maybe then no issue.

received this email after insulting claude

@sporadica More people chatting with ai or using ai tools, maybe?

this is really really great but...why? i don't see any evidence of this in my life, friends+family, etc, so i have to say i'm inherently distrustful of this data. is it really? and if so, what's causing that?

@LuizaJarovsky It is not by definition of the word, atleast not quite yet, but almost there.

Unpopular opinion: AI is NOT conscious.

@rudrank Cod-ex

Is it Co-dex or Code-x pronunciation wise

@BacLeodiv To reallocate compute I assume

Why did OpenAI shut down Sora?

@thsottiaux @riadbenguella I think these people like claude because of how instant and responsive it feels. Gpt5.5 does the better job

@riadbenguella At least share your wisdom with me

I forced myself to switch to Codex App and GPT 5.5 for some days now, I'm going back to Claude App to Opus 4.7 right away. I need to stop suffering. I don't know what all the fuss to move to Codex is about tbh.

@AnthropicAI I dont... anymore.

How do people seek guidance from Claude? We looked at 1M conversations to understand what questions people ask, how Claude responds, and where it slips into sycophancy. We used what we found to improve how we trained Opus 4.7 and Mythos Preview. anthropic.com/research/claud…

@AgorithmAg It must be tricky for them to get gpt5.5 to understand when a user wants an image vs a text response

Has anyone else noticed this GPT-5.5 glitch? The model appears to start “thinking in pictures” / generating a visual output, but the image never actually populates. It just stalls or returns text instead. And after that, the chat seems to get rerouted to GPT-5.4, despite 5.5 being selected. This looks less like a normal failed image generation and more like a routing/UI failure. #gpt55 #chatgpt55 @OpenAI @sama

@0xSero @grok what is the mimo v2.5 token cost

I am blown away by MiMo-V2.5 It's so steerable, I didn't like MiMo-V2 This is self hosted btw, 125 tok/s across 2 sessions 4k prefill tok/s It's updating my website + editing a longer video I will be posting in a few minutes.

@Adidotdev AGI then ASI

What’s next after AI ?

@ChatGPTapp It is clear to see we have achieved agi...

at long last

@FlippedRay aipedia.wiki - a wikipedia for ai tools

Founders, what are you shipping? Drop your link Let’s send traffic your way