Daily Archives: October 1, 2024

[2024 dev2next] gen ai panel

Posted on by
Reply

Intro and one of the mic runners: Ixchel Ruiz

Panel:  Frank Greco,  Brian Sletten, Neal Ford, Micah Silverman

For more see the table of contents

Opening remarks

  • The people who made money in the gold rush made the tools
  • We’re supposed to be the experts; start using
  • AI is not going to take your job, but the person who knows how to use AI well will take your job
  • Snyk has a mandate should be using AI at some point every day
  • If you think this isn’t going to change your job, you aren’t paying attention.
  • Tech journalism is dead; don’t be a credulous idiot and believe PR
  • 28% task competition in tasks for junior devs and none for senior
  • 41% increase in rewrites
  • Radical decrease in moving code around. Keeps adding code, not looking reuse.
  • Don’t want junior devs adding garbage code nobody needs

Q&A

  • Language model selection? hard question. Need to build something quick and iterate. A lot of moving parts in a RAG system. Consider cost (latest and greatest more expensive, more work inference stage costs more). Excel is an abstraction and we know how it works. LLMs are nondeterministic and black boxes.
  • Tech debt? need guardrails to protect against blasting code. Need whether came from junior dev, senior dev, or AI. Dev are more trusting of code from LLMs and falsely believe it is more secure. In past devs, were more pessimistic and verified more. Don’t yet have best practices for probabilistic systems.
  • Have to be careful with prompts with natural language vs turning complete language. Is it a new programming language that looks like natural? In near future, will have a LLM whisperer on each time.
  • News article where tried to get ChatGPT to admin sentiment? we anthropomorphize., Turning test not enough. Arc test (https://lab42.global/arc/) working on better approach. (Abstract and Reasoning Corpus). Solving problems by recognizing new patterns. In field, people saying LLM not the future. In 70s, Eliza “showed” computers could talk, but really parlor trick. Currently in AI hype cycle. Need people who understand limits of mind/limits of what possible. Not on verge of generalized AI/sentience. May not be in our lifetime if even possible. Plenty of natural stupidity.
  • LLMs trained on internet text and generate vast amounts of text which put on internet. When pollute internet to point can’t be trained? on the cusp. “Dead internet” theory where generated content exceeds humans. What happens when people don’t create new poems and creativity. “AI has taught me to believe in a soul because I’ve seen art created without it”
  • Definition of AGI? ARC competition. Referenced books for why not on cusp [didn’t really answer]
  • Reused joke from yesterday about the real changes are in AV, not in AI (when the mic didn’t work)
  • AI fundamentally lies to us; we call hallucinations. Companies say LLMs wouldn’t exist if couldn’t break copyright laws and 2/3 of ChatGPT users present results as own work. Integrity of crypto bros? Industry has ignored ethics for so long. Physists brought into fiction as evil once could destroy world. We are next as bad guy. Youtube on apology tour for dumbing down culture. Project Nightshade lets artists poison art to confuse LLMs. [it adds a pixel layer to categorize incorrectly]
  • AI tooks that help with daily work cycle? Assembly AI API to create transcript from audio, Copilot, Codium (suggests tests). Warp terminal – creates regex from standard English.
  • Prove work made by human vs AI: False positive rate too high. Need ethics. Ex: should have musicians for making music. Teacher added white on white text in test question so could tell if cheating. Unfortunately not sustainable or scalable
  • Open source LLMs: different than what used to with open source. The key is the data. Not open source if don’t say where data coming from legally. Chain of thought makes beefing up model less important due to post processing. Asymmetric power between big tech companies and others. How compete? Microsoft doesn’t have a Windows dept; it is spread out over different departments.
  • Hiring changing narrative especially for recent grads? AI or other job market trends? Yes. Bias if train on resumes with western names or traditional education. Will be fallout. Recent story: manager submitted resume and it got rejected; fired HR. AI is the new electricity where just expect it. Difference is we understood electricity before started using. Hype cycle were AI needs to be on resume to get attention. In NY, big companies hiring junior people expecting AI to help them out. Market for senior folks is dead.

Closing thoughts

  • Learn things. Mediocre people trying to use AI for competitive advantage. Use as tool to be better.
  • Education. AI is not a search engine. Don’t use it as one.

My take

The format was audience Q&A. I enjoyed reading about the ARC project and Nightshade. Great audience questions and great end to the day.

[2024 dev2next] customgpts

Posted on by
Reply

Speaker: Ken Kousen @kenkousen

For more see the table of contents

Notes

  • Goal: Customize ChatGPT without coding
  • Useful for virtual assistants, automate repetitive tasks and shape AI behavior (within limits)
  • GPT Builder: create profile picture, specify leading questions, upload files (useful for own info or diff since gpt last trained), enable code interpreter, publish via a link or public “GPT Store”
  • The GPT Store is just a public link and search. There’s no money

chatgpt.com

  • Explore GPTs in left nav
  • Can search for or browse. Lots of available ones.
  • 4-5 million custom GPTs. Bar to creating is very low
  • Ken made Pragmatic Assistant with rules from PDF and editor rules. Ran chapters through guide. [Janeice made a code version of this for our book; no AI though, long predated ChatGPT]
  • Like a skin on ChatGPT

Demo

  • CustomGPT with text from Venkat’s Agile book
  • Lets choose how communicate – formal, casual, pirate speak, shakespeare, etc [I’ve used chatpgt for western stuff for coderanch a few times]
  • Configure tab – description, instructions for GPT to use (like trying to sell the book), 4 generated conversation starters so users see some prompts.
  • Click on upload files to give training data (in this case Venkat’s book). Takes care of all the RAG steps. Limit on number and size of attachments. Was able to upload 8 books.
  • Give it capabilities like web browsing to use certain sites, DALLE-E, code interpreter
  • Instructions is misleading as have way more room than actually do.
  • Can keep private, sharing via the link or via the GPT Store
  • Gets Ken’s name wrong. Loses the “s”

Trying it out

  • Outputs in Markdown
  • Did try to sell book per instructions

Stats

  • 10 files per GPT
  • Text, spreadsheets, presentations, images,. etc
  • 2 millin tokens per file
  • 20MB for images

“Security”

  • GPT may share file contents.
  • Files can be downloaded when Code Interpreter is enabled
  • [I experimented with Venbot: had it tell me the books available, the table of contents of one, the sections in ch 1 and the full text of two sections. Then I ran out of free tokens for a few hours. When I asked for all of ch 1 it gave me a little and prompted to read the book]
  • Only reference to copyright is in the docs of using free materials

Venbot

  • https://chatgpt.com/g/g-LsSBgJX2D-venbot-5000
  • Demo was fun
  • Cool that it figured out the weather from the location

Actions

  • GPTs allow you to define Actions – external API. Published via OpenAPI spec (what we used to call Swagger)
  • Doesn’t work that well. Easier to write code.
  • ActionsGPT can help generate
  • Many limitations: no customer headers, must be same domain (except google, microsoft and adobe oauth domains), 100K request/response, 45 second timeout, text only

Code version

  • The website was NoCode
  • Showed using langchain4j
  • Can write own logic and will identify. Langchain will call

Problem

  • Custom GPT has name on it
  • When wrong, looks like you did it

Competitors

  • Claude AI – can only share with teammates (via team subscription), limited number of resources. Two books fit. Can’t access internet.
  • NotebookLM from Google – can generate stuff like a read only FAQ based on Gemini, Can generate a study guide (short/long essay questions with answers). Also has audio overview. Meant to be a study tool from docs, websites, and youtube (transcripts)

My take

It was cool seeing a demo. Also, the interaction with Dave Thomas for Pragmatic prompts was fun. I played some with Venbot and some other GPTs while Ken was talking which was also fun. Especially getting it give me parts of the book.

[2024 dev2next] learning to say no without being a jerk

Posted on by
Reply

Speaker: Christina Aldan @luckygirliegirl

For more see the table of contents

Saving the day

  • Overcommit
  • People get used to asking last minute
  • Others “can’t”
  • Wake up call – physical health/carpal tunnel

Boundaries

  • Sound – headphones, cell phone policy, meeting facilitation
  • Nonnegotiatables – core values. Deal breakers
  • Time – deliverables and more
  • Physical – handshakes, taking breaks, hugs, solo lunches
  • Mental/emotional – communication, delegating, saying no, avoiding gossip
  • Material/financial – salary, benefits, office space, equipment

General

  • Feel stuck and come out fighting when backed into corner

Why we resist boundary intrusions

  • Missed opportunities
  • Want to help – little things expand and now you own them
  • Want people to like us
  • Think have to take on everything
  • We are having fun. but even the fun things take energy
  • Conflict avoidance
  • Avoid being a jerk. Some people take no as insult
  • Fear of abandonment
  • Fear of missing out (FOMO)
  • Fear of not being good enough
  • Fear of imperfection
  • Fear of not belonging
  • Fear of change
  • Fear of judgement

Important skill

  • Being able to say no sets boundaries
  • Sets expectations of others in relationship
  • Rules must be followed; create own
  • Can focus more
  • Multitasking is not a thing; need to focus
  • Stay connected to purpose
  • Good fences make good neighbors; people know what to expect

Saying yes all the time

  • Sacrifice gym, personal things
  • Sick too much. Used to plan 10 days to be sick.
  • Always busy; can’t slow down
  • Crash
  • Work is mediocre at best; significantly more mistakes when rush
  • Cancel on friends last minute – “flaker friend”
  • Resentful when tired

Saying no

  • Value own time
  • Think about whether feel obligated – can send to resources or offer to help with a part
  • Think about what it would take to make it an emphatic yes. ex: for negotating contracts and salaries
  • Gamify saying no. Tell people practicing. Have people ask silly yes/no questions.
  • Decide; if you don’t honor your boundaries why should someone else

Hack your brain/emotional intelligence

  • Change your password; change your mind. ex: “NoWayJ0$e” or “NotGoingToDoIt” and log out each time. Forces you to type it a lot and brings to forefront of mind and attention.
  • Shift perspective – third person perspective as if on tv. See relationships and reactions
  • Calming techniques; tapping solutions audio book – takes time to convince brain willing to shift
  • Practice!
  • Self directed study – ex: read something every day, social media, listen to audio, etc
  • Set reminders on calendar. Brain processes images faster than anything so glance at it and see pop up as constant reminder about saying no
  • Writing on paper – involve more senses
  • Role play – had conversation in head

Have phrases

  • “Thanks so much for thinking of me. Unfortunately I have another commitment. I am copying X who is an expert on the subject and more than qualified to speak at your event”
  • “I am not the est person to help out with this. There’s probably someone more appropriate to ask”
  • “If this were any other day/time I would do it. Unfortunately I have another commitment”
  • “It just don’t work with my calendar:
  • “This doesn’t meet my needs now, but I will keep you in mind for future reference” – stops repeat spam on linked in
  • “No. Unfortunately it looks like it won’t work for me”
  • “Thank you for thinking of me. Unfortunately my calendar is full at the moment. How is X for you”
  • “I just don’t feel like I could give you my full time and attention on this”
  • “Thanks for asking me, but I’m already committed to something that day”
  • “I promised my business partner I wouldn’t take on any more projects”
  • “I can’t do that, but let me tell you what I can commit to”

Warnings

  • Be honest – don’t defer to next month if don’t want to do it
  • Beware of reluctant yes where “yeah, I think I can do that” and then it immediately gets bumped. Either emphatic yes or definitive no.
  • “No” is a complete sentence

My take

This was awesome. Faced paced and lots of ideas. My session is right after this and I have a few things I can reference!