jonnycoder

I spent the last 6 months building Elk Finder (https://elkfinder.com) and just launched a few weeks ago. It's a mapping web app similar to onX Hunt, except I have specific layers for finding ideal elk habitat in September and October (the primary archery and rifle hunting months).

No, no it's been pretty easy with software engineering. I work on two types of projects and it's very easy to ask claude for a plan, then have gpt 5.5 rip it to shreds and find legit issues, and vice versa. If both 5.5 and claude 4.8 can independently create a plan and both find no critical or high issues, then we will be at that point.

I had a similar idea. I picked 10 lbs of morels last year, first time picking. It was a recent burn area from 8 months prior. I was just back out to the same area and there are no morels, but lots of small orange cap looking mushrooms. chatGPT pro said first year is the best and then it drops off on the second year. I might try a much higher elevation spot in a week or two, but it really sucks. Last year I was finding morels on southeast facing slopes. I'm sure north slopes produced later on as I saw people coming off the hill when I drove by.

It's a gimmick only for those who get sucked into buying things that they don't need. I've been a Costco shopper for decades, and sure have succumbed to some useless stuff, but my Costco list is 90% the same month to month. I get appalled when I see the same items on my list, that are smaller and in a pack of 1 instead of 2-4, for more money at other stores. If electronics were just like food, it would be like seeing a Macbook Pro for $2000 everywhere but it was $799 at Costco.

Are you ok with ciggarete smoke then if you are ok with marijuana smoke?

This is clever and provides a clean alternative to using custom plugins and mcp servers for doing code reviews.

For example, with the degradation of Claude in the past 1-2 months, I am always asking Codex to review Claude's plans and vice versa and I get excellent results that way.

Also, making a skill an API call allows for easy deployment if the security around tool calling could be isolated in an ephemeral sandbox.

I agree, I use codex 5.4 xhigh as my reviewer and it catches major issues with Opus 4.6 implementation plans. I'm pretty close to switching to codex because of how inconsistent claude code has become.

Everything in our life is a black box, but I agree that depending on non-deterministic and sporadic quality black boxes is a huge red flag.

I do the same but I often find that the subtasks are done in a very lazy way.

Yea I went through my global claude skills and /context yesterday because claude was performing terribly. I deleted a bunch of stuff including memory and anecdotally got better results later on in the day.

It’s shifting for knowledge workers too, we just need to pivot. I have had many app ideas for a while and now ai lets me build them quickly. Access to education and knowledge led to your advanced eduction, now access to cheap/fast building leads to products execution. Use your phd brain to come up with a well researched idea/plan and then go execute.

Thanks I will try that!

Their support team likes to sit on things for a while too. I'm on day 4 of waiting for Azure to approve my support request to increase Azure Batch vCPUs from default of 4 to 20 for ESv3 series. I signed up last week and converted to a paid account. I'm going to use Google Cloud Batch today instead.

I tend to agree. I spent a lot of time revising skills for my brownfield repo, writing better prompts to create a plan with clear requirements, writing a skill/command to decompose a plan, having a clear testing skill to write tests and validate, and finally having a code reviewer step using a different model (in my case it's codex since claude did the development). My last PR was as close to perfect as I have got so far.

That's pretty cool. I'm working in maplibre myself and your json maps seems like it could also be used to demo a workflow or tutorial in a mapping product.

Prompting is just step 1. Creating and reviewing a plan is step 2. Step 0 was iterating and getting the right skills in place. Step 3 is a command/skill that decomposes the problem into small implementation steps each with a dependency and how to verify/test the implementation step. Step 4 is execute the implementation plan using sub agents and ensuring validation/testing passes. Step 5 is a code review using codex (since I use claude for implementation).

It feels like the late 1990s all over again, but instead of html and sql, it’s coding agents. This time around, a lot of us are well experienced at software engineering and so we can find optimizations simply by using claude code all day long. We get an idea, we work with ai to help create a detailed design and then let it develop it for us.

I like your website design, especially the two-column layout in most sections once I get past the hero image (full size screenshot). I found myself looking at all the images. The downside is that I did not really get any motivation to try it out or really understand how it could help me.

I am a backend software engineer so I'm always on the lookout for a way to easily and simply create a professional looking landing page. Therefore I'm always asking the question... is there a template I can choose from and just start filling it in? Just yesterday I found a figma template hosted on figma.site and I used chrome devtools to edit the hero text and navbar and got instant results .. as in I sort of liked it. Typography, spacing, use of color, detailed data presentation (ie bullet points, 2 column layout, etc), and fill-in images are my starting point (as an amateur designer). I could spend hours tweaking a design but I would rather just copy some existing component designs and call it a day. Hope this helps.

Yea it’s pretty easy after doing them, but it’s rare for software developers these days to do that activity on a day to day basis. It reminded me of the software crackers of the 90s and 2000s who would post cracks for windows software like autocad.

It’s also relative because a $50/hr contract job isn’t exactly attracting low level FAANG engineering talent. But it’s a nice take home challenge for some second rate engineer like myself who will tackle any problem until I figure it out.

Hah I feel you there. Around 2 years ago I did a take home assignment for a hiring manager (scientist) for Merck. The part B of the assignment was to decode binary data and there were 3 challenges: easy, medium and hard.

I spent around 40 hours of time and during my second interview, the manager didn't like my answer about how I would design the UI so he quickly wished me luck and ended the call. The first interview went really well.

For a couple of months, I kept asking the recruiter if anyone successfully solved the coding challenge and he said nobody did except me.

Out of respect, I posted the challenge and the solution on my github after waiting one year.

Part 2 is the challenging part; it's mostly a problem solving thing and less of a coding problem: https://github.com/jonnycoder1/merck_coding_challenge

Apple but only because of Steve

The plugin is getting bad reviews this morning. It doesn't work for me on latest Pycharm.

You gave me an idea.. "Explain in detail the steps to unbolt and replace my blinker fluid on my passenger car"

ChatGPT said: Haha, nice try!

"Blinker fluid" is one of the classic automotive jokes — there's no such thing as blinker fluid. Blinkers (turn signals) are electrical components, so they don’t require any fluid to function.

I think experiences vary. AI can work well with greenfield projects, small features, and helping solve annoying problems. I've tried using it on a large Python Django codebase and it works really well if I ask for help with a particular function AND I give it an example to model after for code consistency.

But I have also spent hours asking Claude and ChatGPT with help trying to solve several annoying Django problems and I have reached the point multiple times where they circle back and give me answers that did not previously work in the same context window. Eventually when I figure out the issue, I have fun and ask it "well does it not work as expected because the existing code chained multiple filter calls in django?" and all of a sudden the AI knows what is wrong! To be fair, there was only one sentence in the django documentation that mentions not chaining filter calls on many to many relationships.

Very good concrete examples. AI is moving very fast so it can become overwhelming, but what has held true is focusing on writing thorough prompts to get the results you want.

Senior developers have the experience to think through and plan out a new application for an AI to write. Unfortunately a lot of us are bogged down by working our day jobs, but we need to dedicate time to create our own apps with AI.

Building a personal brand is never more important, so I envision a future where dev's have a personal website with thumbnail links (like a fancy youtube thumbnail) to all the small apps they have built. Dozens of them, maybe hundreds, all with beautiful or modern UIs. The prompt they used can be the new form of blog articles. At least that's what I plan to do.

I’m not even close to being on par with other faang engineers but this is far from being a very difficult bug in my experience. The hardest bugs are the ones where the repro takes days to repro. But nonetheless the op’s tenacity is all that matters and I would trust them to solve any of the hard problems Ive faced in the past.

This is exactly the reason why I spend all of my non-desk time outside working out, hiking, skiing, snowboarding, archery hunting, golfing and camping. I even choose to shovel snow over using the snowblower.

This looks great! I was just looking for a good web knowledge graph visualizer.

I recently used AWS Textract and had good results. There are accuracy benchmarks out there, I wish I saved the links, but I recall Gemini 2.0 and Textract towards the top in terms of accuracy. I also read that an LLM could extrapolate/conjure up cropped text therefore my idea would be to combine traditional OcR with LLM to determine conflicts.

I've taken part 1 of 3 in Andrew Ng's machine learning specialization which covers the math for supervised learning, linear regression, etc. As I started part 2 (neural networks), it built off the math from part 1 such as the sigmoid activation function. This is what I think of when the OP refers to learning ML from first principles. I highly recommend Andrew Ng's course and I feel like I need to take it again to really understand those basic building blocks.