jonnycoder

الشهر الماضيdiscuss

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.

jonnycoder

قبل شهرينdiscuss

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.

jonnycoder

قبل شهرينdiscuss

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.

jonnycoder

قبل 3 أشهرdiscuss

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

jonnycoder

قبل 3 أشهرdiscuss

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.

jonnycoder

قبل 3 أشهرdiscuss

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.

jonnycoder

قبل 3 أشهرdiscuss

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.

jonnycoder

قبل 3 أشهرdiscuss

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

jonnycoder

قبل 4 أشهرdiscuss

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.

jonnycoder

قبل 4 أشهرdiscuss

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.

jonnycoder

قبل 4 أشهرdiscuss

Thanks I will try that!

jonnycoder

قبل 4 أشهرdiscuss

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.

jonnycoder

قبل 4 أشهرdiscuss

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.

jonnycoder

قبل 4 أشهرdiscuss

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.

jonnycoder

قبل 4 أشهرdiscuss

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).

jonnycoder

قبل 4 أشهرdiscuss

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.

jonnycoder

قبل 5 أشهرdiscuss

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.

jonnycoder

قبل 10 أشهرdiscuss

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.

jonnycoder

قبل 10 أشهرdiscuss

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

jonnycoder

قبل سنتينdiscuss

I have the same experience. I've been unemployed for 5 months as a Senior Software Engineer and I hit most of the job requirements. The only skill I don't directly match is React development for full stack jobs, but I am building an LLM app in React so that I can fix that hole. Speaking of LLM, I'm surprised I'm not seeing any job skill requirements for LLM related topics or even vector database experience. Are the bigger companies so far behind the curve here?

comments