Problem-solving is at least 50% of every job in tech and science.
Mastering problem-solving will make your technical skill level shoot up like a hockey stick. Yet, we are rarely taught how to do so.
Here are my favorite techniques that'll loosen even the most complex knots:
@realhyderabad86@SulliRonni61327 NRIs buying using dollars is probably the very reason why 99% of people, working in India and paying taxes here, are not able afford the homes right now. Builders are building to lure NRIs, which is of course their right to do so as well.
We often discuss DevOps, but the 'Ops' world extends beyond just DevOps. Integrating various Ops disciplines, including the emerging trend of LLMOps, with different aspects of product development, is enhancing our ability to create superior software.
https://t.co/GMYyDMsxsm
@KTRBRS@BRSparty Though I am an admirer of BJP, I doubt whether I’ll see any other dynamic minister as @KTRBRS was…look at the grace with which he is congratulating…
Looks like a good idea. Not sure about the cost effectiveness and the actual usefulness as yet. If possible, can we consider and try it on our ORR and busy highways of Telangana ? @KTRBRS
If you are running @playwrightweb tests on AKS using the official docker image, what’s your resource and memory limits? How much memory is needed for it to be running? @debs_obrien any suggestion? Is there a way to print the progress so it can be see? #playwright#playwrightweb
No more repetitive questions.
Technicians have access to your entire chat history, for a more informed and efficient conversation. Build GPT-automated customer support with Azure Communication Services. https://t.co/GHRpUWjO0W #AzureServices
We've arrived at the grand finale - the last webinar in our much-anticipated series on #MicroFrontends 🚀
Register now to learn more on how to overcome common micro-frontends challenges!
See you on Thursday
#frontend#javascript#aws#architecture#web
https://t.co/b9FEKytZUo
LLMs and Their Human-like Reasoning Capabilities - Fact or Fiction?
Research into enabling Large Language Models (LLMs) to display human-like reasoning has been a hot topic. However, some others have argued that LLMs aren't capable of reasoning given that are glorified next-word predictors.
Here is where we are today -
Chain of thought (CoT) reasoning - Prompting a "chain of thought"—a series of intermediate reasoning steps—can significantly improve the performance of LLMs in complex reasoning tasks.
The human brain typically decomposes a math problem into intermediate steps and solves each step before giving the final answer: “After Jane gives 2 flowers to her mom she has 10 . . . then after she gives 3 to her dad she will have 7 . . . so the answer is 7.”
The basic idea behind CoT is to prompt the model with some examples of these types of problems and the step-by-step reasoning involved in solving them. By prompting in this way, the model can decompose the problem similar to the human brain and solve for it.
LLMs when prompted with just eight chain-of-thought examples, achieved state-of-the-art accuracy surpassing even fine-tuned versions of GPT-3
CoT prompting helps in improving airthmetic, commonsense, symbolic and multi-step reasoning capabilities of the LLM
That said, the CoT prompting is fairly limited. It depends a lot on the quality of the prompt and the model doesn't have memory and the prompt size is limited by the model's context length.
Recently researchers at DeepMind released a paper that outlines the Tree of Thoughts (ToT) framework. It addresses the shortcomings of existing approaches that do not explore different continuations within a thought process or incorporate any type of planning, lookahead, or backtracking to evaluate different options.
ToT frames any problem as a search over a tree, where each node represents a partial solution with the input and the sequence of thoughts so far. It allows LMs to explore multiple reasoning paths over thoughts, each thought being a coherent language sequence that serves as an intermediate step toward problem solving.
The ToT process involves four key steps:
- Decomposing the intermediate process into thought steps.
- Generating potential thoughts from each state.
- Heuristically evaluating states.
- Deciding what search algorithm to use.
The ToT framework allows LMs to perform deliberate decision making by considering multiple different reasoning paths and self-evaluating choices to decide the next course of action. It also enables looking ahead or backtracking when necessary to make global choices.
The framework is versatile and can handle challenging tasks. It also improves the interpretability of model decisions and the opportunity for human alignment, as the resulting representations are readable, high-level language reasoning instead of implicit, low-level token values.
In practice, the ToT framework has significantly enhanced language models' problem-solving abilities on tasks requiring non-trivial planning or search.
In the Game of 24, while a model with chain-of-thought prompting only solved 4% of tasks, the ToT method achieved a success rate of 74%.
ToT is a prompting framework has well and has the same fundamental limitations as the CoT framework. ToT needs careful thought decomposition and generation, and relies on heuristics for evaluating states and deciding on the search algorithm.
However it's important to remember that while LLMs can mimic certain types of reasoning to a certain extent, but it's not the same as human reasoning.
They don't have the ability to understand, self-correct, or make judgments based on a deep understanding of the world. They're more like really good actors who can deliver their lines convincingly but don't actually understand the plot of the play.
In summary, AI is still extremely early when it comes to reasoning and we may need a another significant breakthrough before LLMs can really measure up to humans.
Story Points don't work.
Even Ron Jeffries, who invented them, said he was sorry years ago.
And not only did he apologize, but he called the whole estimation idea "Evil."
Unfortunately, too many teams still use these points to estimate their work.
Story Points is a made-up metric to estimate work effort, not time. The goal was to prevent management from misusing estimates.
But it didn't work.
Every team I've ever met keeps a conversion table to translate back and forth between points and time. Some will never admit it, but go and talk to the folks doing the work.
Look at me and tell me I'm wrong.
But it gets worse:
Teams use points to decide how much work they can finish. But how can they do that without talking about time?
The effort to do something is not the same as the time it will take to finish it. This is especially true when planning an iteration with many people and tasks.
It's clear now: Story Points don't work.
What's the alternative?
I'll let the people who manage projects for a living offer their alternatives, but I can tell you what I've done.
As I got older and wiser, I stopped with the estimation charade altogether. I had my teams focus on short iterations with constant feedback from stakeholders.
From the "scope, budget, and time" triangle, I always tried to keep two of them variable and fix the third one.
If the customer was looking for a specific scope, we had a variable timeline and budget to finish it. We kept the scope and time flexible if the budget was non-negotiable. And if we had to deliver by a specific date, the scope and budget were on the table.
Every company is different, and this doesn't work for everyone. But if it does, I hope you stop the charade.
I'd love to hear about your experience estimating software. What crazy things does your company make you do?
@khushbooverma Did you pay in the new financial year, or in the same financial year as you received it? I’m going thru same process and yes we need to pay the tax.. a bug in the system