331–340 of 550 posts
Only more mental exercises to avoid reading the writing on the wall: LLM DO NOT REASON ! THEY ARE TOKEN PREDICTION MACHINES Thank you for your attention in this matter!
"Wow, AI will replace programming languages by allowing us to code in natural language!" "Actually, you need to engineer the prompt to be very precise about what you want to AI to do." "Actually, you also need to add in a bunch of "context" so it can disambiguate your intent." "Actually English isn't a good way to express intent and requirements, so we have introduced protocols to structure your prompt, and various k…
Only without all that pesky determinism and reproducibility. (Whoever's about to say "well ackshually temperature of zero", don't.)
Earlier quoted context omitted.
Why not? What is so special about reasoning that you cannot achieve by predicting tokens aka. constructing sentences?
If you don't understand the difference between a LLM and yourself, then you should talk to a therapist, not me.
> Building powerful and reliable AI Agents is becoming less about finding a magic prompt or model updates. Ok, I can buy this > It is about the engineering of context and providing the right information and tools, in the right format, at the right time. when the "right" format and "right" time are essentially, and maybe even necessarily, undefined, then aren't you still reaching for a "magic" solution? If the definit…
1 - LLM Tends to pick up and understand contexts that comes at top 7-12 lines.Mostly first 1k token is best understood by llms ( tested on Claude and several opensource models ) so - most important contexts like parsing rules need to be placed there.
2 - Need to keep context short . Whatever context limit they claim is not true . They may have long context window of 1 mil tokens but only up to avg 10k token have good accuracy and recall capabilities , the rest is just bunk , just ignore them. Write the prompt and try compressing/summerizing it without losing key information manually or use of LLM.
3 - If you build agent-to-agent orchestration , don't build agents with long context and multiple tools, break them down to several agents with different set of tools and then put a planning agent which solely does handover.
4 - If all else fails , write agent handover logic in code - as it always should.
From building 5+ agent to agent orchestration project on different industries using autogen + Claude - that is the result.
Only more mental exercises to avoid reading the writing on the wall: LLM DO NOT REASON ! THEY ARE TOKEN PREDICTION MACHINES Thank you for your attention in this matter!
Earlier quoted context omitted.
What is reasoning? And how is it apparent that LLMs can't reason? The reality for me is that they are not perfect at reasoning and have many quirks, but it seems to be that they are able to form new conclusions based on provided premises. Genuinely curious why you think they can't.
> Genuinely curious why you think they can't. Show me _ANY_ example of novel thought by a LLM.
Only more mental exercises to avoid reading the writing on the wall: LLM DO NOT REASON ! THEY ARE TOKEN PREDICTION MACHINES Thank you for your attention in this matter!
During pre-training, yeah they are. But there's a ton of RL being done on top after that.
If you want to argue that they can't reason, hey fair be my guest. But this argument keeps getting repeated as a central reason and it's just not true for years.