Dennis Gorelik

Today (and few days ago) I talked with a founder of botson.ai - Dan.
Dan told me how amazing their tech team is in chatbots and jobs matching technology.

When I asked Dan about specific details about what made their job matching algorithms so amazing -- Dan told me that integration of their javascript into our job board is super-easy.

That javascript would tag job seekers who visit our job board with botson.ai cookie.
If job seeker has an open Facebook session - then botson.ai would sign job seeker up for jobs chatbot on Facebook messenger.
Then the chatbot would send jobs that it thinks are relevant to what job seeker is searching for.

I wanted to try that amazing technology before integrating it into our job board and asked Dan to give me a link to signup.
Dan gave me a link, but it did not work. Dan gave me another link. The second link did not work either. The third link worked and I received Facebook message from "Maya - Recruiter".
"Maya" was moderate and only messaged me when I messaged her.
However job matches were not relevant.
I called myself "Monster Botsonai" in a signup form (on the affiliate web site that Dan gave me links me to), so Maya initially called me "Monster", but then corrected itself based on my Facebook profile.

This is my chat with "Maya - Recruiter":
==================
[Maya]
Hi Monster 😊
Following your request for jobs near 32081 here is a selection just for you

[Facebook]
You agreed to have Maya - Recruiter send you updates. Replying will allow Maya - Recruiter to see info you've made public.

[Maya]
Warehouse Associate
We're Hiring Warehouse Associates!. Pay Rate Picking and packing Loading and un...
More Details
Apply Now

[Dennis]
View More Jobs

[Maya]
Pool Technician II
Position Summary:This position is primarily responsible for the daily maintenanc...
More Details
Apply Now

[Dennis]
I look for different jobs

[Maya]
Experienced Auto Hauler
We are a new and growing company that is actively seeking experienced auto haule...
More Details
Apply Now

[Dennis]
[Clicked on "Caregiver jobs"]

[Maya]
Caregiver / Resident Assistant / Personal Care Assistant / CNA
Join a Family, Serve with the Best - Benton House at OakleafAre you a CNA lookin...
More Details
Apply Now

[Dennis]
Can you send me different jobs?

[Maya]
Order Puller - Warehouse
Join the Remedy Family ~ Build Your Career The Remedy Staffing Jacksonville Team...
More Details
Apply Now

[Dennis]
What about C# sql jobs?

[Maya]
Local Landscapers Wanted!
Over 25 million homeowners have trusted HomeAdvisor 1800Contractor to help the...
More Details
Apply Now

[Dennis]
SQL and C#

[Maya]
Hi 😊 I'm an automated HR service and I can only assist you to find more job offers.

I’ll do my best to help you with your search. What job position you are looking for?

[Dennis]
c# sql

[Maya]
Hi 😊 I'm an automated HR service and I can only assist you to find more job offers.

I’ll do my best to help you with your search. What job position you are looking for?

[Dennis]
Software developer

[Maya]
IT Software Developer Senior
EverBank is more than just a bank; it's the evolution of an idea. Traditional fi...
More Details
Apply Now

[Dennis]
C#

[Maya]
Hi 😊 I'm an automated HR service and I can only assist you to find more job offers.

I’ll do my best to help you with your search. What job position you are looking for?

Dennis, was this helpful for you?
Do you want to see more job openings? Just tell me what kind of job position you are looking for 😊

[Dennis]
oncology nurse

[Maya]
Hi 😊 I'm an automated HR service and I can only assist you to find more job offers.

I’ll do my best to help you with your search. What job position you are looking for?

[Dennis]
nurse

[Maya]
Registered Nurse (RN)PRN - Endoscopy
Job ID: 198390Registered Nurse (RN)PRN - EndoscopyJacksonville, FloridaRegular/R...
More Details
Apply Now
==================

So it looks like Botson.ai chatbot recognizes some large job search categories (such as "software developer" and "nurse"), but does not recognize more specific skills (C#, SQL, oncology).

My conclusion is that the intelligence behind the chatbot technology is not ready yet, but the idea to use chatbot for job search - looks interesting.

After I complained about disappeared "Bounces" and "Complaints" graphs, Amazon SES team brought them back.

Muhammad contacted me on LinkedIn:
===============
M: Hi Dennis,
As one of my connections, I wanted to quickly reach out to see if you have any current or future opportunity for me?
...
I am based in Islamabad Pakistan.
{Long list of buzzwords and self-praise skipped}
D: What's your hourly rate?
M: Hi Dennis, thanks for your response.
I am happy if I can get $40+ /hr. Incase of remote opportunity $20/hr is good.
===============

We chatted on LinkedIn a little about his participation in nTaskManager project.
I pointed out to a misspelling in his resume "Windows Azuer" (which is not a good sign), but he fixed it (which is a good sign) and said "thank you" for that.

I was not able to get answers from Muhammad to my specific technical questions and was considering dropping it, but Muhammad offered to talk on Skype.
So I decided to try and see what would happen. In particular, my goal was to learn how text chat correlates with voice conversation over Skype.
Muhammad proved to be consistent: he could not answer my specific tech questions in text chat, and he could not answer my specific questions in our voice conversation.

Transcript of our voice interview
--------------------
D: Hi Muhammad.
M: Hi Dennis, how are you.
D: Let’s start with question about email that this nTask sends (*1). Did you create this email?
M: Actually, I created this with the team. It was not only my task. I think it was team of 5 persons. I see your screen.
D: So, yes, I’m talking about this email. Did you participate in any way in creating this email.
M: Actually, my participation was only technical: creating technical design, ..., creating technical implementation , ...
D: So, did you do anything about this email. Anything. Any activity. Did you put any work into this email?
M: There are 2 things: one is content and second one is how email is being sent. What I implemented is to send emails. This email template was designed by our designer, and content was designed by the owner of this application. My role was to write code, so this email will be sent.
D: When this code was (*2) ... are you saying you wrote code that was sending this email? Or you are not saying this? Or you did not do it?
M: Sorry, I could not get what you said.
D: Did you write the ... I still cannot understand what you did here. Did you do anything here? Or you actually wrote code for sending this email. Or was it somebody else who was doing it?
M: I was writing the code.
D: You were writing the code. Ok. How many developers were writing code that sends this email?
M: I had one front-end developer...
D: Uh-huh.
M: ... and one SQL guy with me, and I was only backend developer. And the code was written in C#. And we were using Mongo DBs database.
D: So could you explain, in this email, what was the backend work and what was the front-end work, and which part did you do, specifically? In this email.
M: Actually, as a backed it is, actually MVC single-page application. And this is using ...
D: [Interrupting] Ok, now you mention MVC. Single page application. What does it have to do with MVC? Like this email – what does it have to do with MVC?
M: Actually, MVC is the main framework for this.
D: What do you mean? Are you saying you are using MVC in order to create email?
M: No-no-no. Definitely there is an application. It’s a complete architecture. Having multiple ... for database, operations, sending emails...
D: So, we are talking specifically about email. Do you understand it, right? We are talking specifically about sending email. I am asking you specifically about this email. You were mentioning MVC. Why were you mentioning MVC in the context in the email?
M: Sorry, I were talking about overall architecture ...
D: [Interrupting] No, we were not talking about overall architecture. I was talking, specifically, about this email. I am not talking about overall architecture. Did I say “overall architecture”?
M: N ... this specific email – there is nothing special, just Microsoft [unclear] just register. Request will go to the server. Once your account is created. And we are sending email to just verify you enter your own email address, to avoid spamming.
D: Uh-huh.
M: There is not special, there is just as way for emails.
D: Ok. And?
M: What do you mean “and”? ... I think there is nothing special or complicated in sending email.
D: Ok, Muhammed, here’s what I noticeD: you do not answer my questions. Ok? It looks like you do not even understand them.
M: Sorry, can you repeat the question?
D: I asked you several questions. During this conversation (while we are talking for, like, 3 minutes now) I asked you several questions. You answered almost none of them.
M: Yes, can please start with one by one. I will be answering.
D: All right. So, one of my question was: “Did I ask you to talk about overall architecture?”.
M: Eh, sorry, I was talking about what is the overall implementation of this project. And you asked me what was your role. I was talking about my role. My role was to create an architecture.
D: Ok, it looks like you, again, did not hear my question. Could you repeat my question before you answer that? (*3).
M: Sorry, actually, when we were talking about few seconds ago, and you just asked what was my role. And my role was from multiple tasks. So, I talked about the architecture and MVC-like things in the context of my role.
D: So, context of your role... Context of your role in what? What do you think I asked you?
M: Actually, I understand it was, there you wanted to ask me what was my role on this application, and I was just explaining my role on this application.
D: On “this” – on what “this” application? What do you mean under “this” application?
M: “This application” means “nTaskManager”.
D: I did not ask you that! I did not. I asked you, specifically, about this email.
Ok, Muhammad, I think there is no point to waste the time. I see what would happen going forward. You do not understand my questions – we are not able to work together. Thank you.
M: Thank you.
D: Bye.
--------------------

Foot notes
(*1) - The email subject is "Complete your nTask Registration". Email messaging is very important for my business, so I decided to start conversation with it.
(*2) - I started asking Mohammad about "when this code was written", but then changed my mind mid-sentence and moved on to the question that focused on his role in creating this email.
(*3) - At this point I sound noticeably angry, and that makes Muhammad a little bit nervous.


What do you think: if interviewee is not able to repeat my question and instead talks about a different topic - is it reasonable to terminate interview at that point?

Short names vs unique names
It is a good practice to use shorter method names, because long names are harder to read.
It is cleaner to call:

candidate.Save();

than:

candidate.SaveCandidate();

But then we end up with multiple "Save()" methods in different classes. For example:

Candidate.cs/Save()
Recruiter.cs/Save()

Problem with non-unique names
If we search our codebase for "Save(" - we would find a lot of methods and method calls. Only some of them would relate to the functionality we actually want to research (for example, we may want to research where "Candidate Save()" functionality is used because we consider refactoring or deleting it).

Plain text search vs code references
Visual Studio allows to find all references to a specific method by right-mouse-clicking on a method name and selecting "Find All References".
So, non-unique method names problem is solved, right?
Not quite.
Visual Studio is not able to track method calls that are made from aspx and ashx files.
Visual Studio is also not able to find method references in the comments.

ReSharper vs vanilla Visual Studio
ReSharper actually is able to find method references in aspx, ashx and even in comments. Until Visual Studio 2015 that worked fine. But since ReSharper team and codebase aged, and Visual Studio switched to new Roslyn compiler, ReSharper team was not able to keep up and delivered only barely working resource hog, that is practically not usable with newer version of Visual Studio (too slow).

Get rid of aspx and ashx files?
It is actually pretty easy to avoid using ashx handlers and use standard C# classes to implement HttpHandler interface.
But what about aspx pages: can we get rid of them too and use only standard C# HttpHandlers?
If we could do that, then we would be able to rely on "Find All References" feature again.
But, unfortunately, getting rid of aspx pages is not that simple. We would have to reimplement a lot of functionality that aspx has.
For example:
- Page PostBack support would be gone.
- Ability to nicely combine HTML code and aspx controls alongside each other would be gone.
- HTML syntax validation would be gone (no HTML syntax validation for C# strings in Visual Studio).

If it ain't broke - don't fix it
Even though it is pretty straightforward operation to convert existing ashx files into standard C# classes (where Visual Studio is able to track all method references) - such conversion is not without its own problems.
- Conversion takes developer's time.
- Code replacement could introduce silly bugs.
- Moving code from class to class makes navigating "svn blame" - a little bit trickier.
So if an ashx handler was working in the solution for many years already - does it make sense to touch it now?

The benefits of code refactoring
In spite of "If it ain't broke - don't fix it" rule - cleaning up code is still needed. If we do not keep code clean (do not delete unneeded parts and do not clear confusing things such as hidden references) - then our codebase would be extremely hard to maintain. Fixing a bug would introduce other bugs. Features would be very hard to add without adding bugs.

It depends
There is no single solution that can be applied to all situations. In software development we consider multiple problems and constantly weigh pros and cons against each other.
For example, out of 11 remaining ashx files, we:
- Deleted one file because we do not use it ("Reduce amount of code when possible" principle).
- Would migrate one file to the standard C# HttpHandler, because today during refactoring a developer missed a method call from that ashx file.
- Keep other 9 ashx files as is ("If it ain't broke - don't fix it" principle).

What are your examples of balancing problems against each other?

Santhosh claims in his resume that he is a Web deveper.
Interview showed that he is probably a web or graphic designer. But not a developer.
He mentioned Javascript, but when I started to talk with him about specific task that could be implemented in Javascript - he quickly gave up.
All people on his team have "Senior System Analyst" title, but from my understanding, Santhosh is a junior at his role.
When describing the accomplishments, Santhosh used word "we". Sometimes "we" meant him, and sometimes "we" meant his team.
Skype audio connection was good (which is not typical for Skype calls to India). That is probably because Santhosh worked (on the bench) from his employer office.
2000 rupees per day ($30/day = ~$700/month).

Unfortunately nothing of what Santhosh can do a meaningful contribution to PostJobFree: we need mostly backend work (middle-tier, parser, SQL queries and database design) or solid UX. Santhosh did not show signs of either of that knowledge.
So I told Santhosh that his skills do not match what I am looking for and asked him if he has any questions for me.
He did not have any questions.
Few minutes later he messaged me:

Santhosh: Hi is any possibility to give one task related to Ui Ux Design and see if I didn't complete we can drop for further or else we will continue as well
Ui Ux/Front-end Development
Dennis: I do not have tasks suitable for your skills

This was a 27 minutes interview.
I should learn to recognize such mismatches much faster.

Early ElasticSearch History
Back in 2010 Shay Banon created first version of ElasticSearch.
Over the years the product matured.
In November 2012, ElasticSearch team received $10M in Series A funding.
Then in February 2013 they received $24M in Series B funding.
That helped them to produce very robust ElasticSearch 1.0 (2014-02-12) and then ElasticSearch 1.6 (2015-06-09) that we currently use.

$70M bloat
June 2014 - $70M Series C funding.
Shay Banon became a CEO and excused himself from active involvement in development and communicating with customers.
That is where the bloat began.
It looks like ElasticSearch team decided that since they have so much money - they can do pretty much whatever they want.
So they broke backward compatibility of their percolator by squeezing percolator into the standard format of ElasticSearch index.

What is percolator?
ElasticSearch percolator does reverse operation to a standard ElasticSearch query.
Standard ElasticSearch query allows our job seekers to find matching jobs.
Percolator allows job seekers to use their job search query in order to create a job alert.
Then when, in the future, new job is posted (by somebody else) -- the percolator is able to find all job alerts that job seekers created. That allows us to notify all owners of these matching alerts about new matching job (within a minute of receiving a job).

Differences between standard search query and percolator query
Because of the reverse nature of percolator, it functions very different from a standard search query:
1) Standard search query should normally produce only 10 results (users is unlikely to read more) and support paging.
Percolator always wants to get all matching alerts (also known as "percolator queries") - not just 10 of them, because every job seeker wants to get notified about new matching jobs to their favorite job alert.
2) Standard search - ranks search results based on the quality of the match (and then order results by descending rank). Such ranking does NOT make sense for percolator (because every job seeker wants to get notified anyway).

Why use standard search index format for percolator?
So why had ElasticSearch team decided to break backward compatibility and merge Percolator into a standard search index format?
This is their excuse:
---
https://www.elastic.co/blog/elasticsearch-percolator-continues-to-evolve
Prior to 5.0, all percolator queries need to be executed on this in-memory index in order to verify whether the query matches. So the idea is that the less queries that need to be verified by the in-memory index the faster the percolator executes.
---
In my first reading of that ambiguous claim I thought that ElasticSearch would be able to automatically detect what percolator queries is ok to skip, so it would, effectively, improve percolator performance.

What actually happened
We spend few days to setup proper experiment and found out that ElasticSearch 5.4 percolator is 3 times slower than ElasticSearch 1.6 percolator (or in other words, ElasticSearch percolator performance degrades proportionally to the version number).

The correct interpretation of that "less queries that need to be verified" claim actually meant that application developer in ElasticSearch 5.4 has an option to tag percolator queries (alerts), and then write code that would help percolator to skip alerts that have no chance to being triggered by a document we percolate.
But the problem is that it is very hard to come up with such "alerts skipping" algorithm. Percolator is so valuable in the first place exactly because of that ability to determine what alerts match and what alerts do not!

The summary
Series C $70M funding encouraged ElasticSearch team to break backward compatibility and produce useless features (such as paging and ranking in percolator) + degrade performance 3x.

Next: ElasticSearch Percolator Bloat - the Defense

I got an email reply from a job seeker to our "Your Best Skills" email:
---
Hello Dennis,

As a black woman in computer science and engineering, I am confused as to why my top job skill in the email you sent me was listed as "black". Please shed some light on this as it is being preceived as quite insensitive. See the attached picture for reference.

Quick investigation showed that her resume explicitly lists:
National Society of Black Engineers
Black women’s Association scholarship
Graduate Advisor for the UCR National Society of Black Engineers (NSBE) Chapter

So I replied:
---
{NameRedacted},

You listed word "black" on your resume multiple times, so it was automatically added as your skill, since you put so much emphasis to it.

You are welcome to rearrange your skills here:
https://www.postjobfree.com/candidate-skills-profile

I already removed "black" skill from that list.

Does it help?
===

I considered removing word "black" from allowed skills list, but then remembered that there are such things as "black belt" (in management) and "black magic".

Besides, some job seekers may actually target jobs where they can reap benefits of affirmative action in big corporations.

Couple of weeks ago we noticed that the same C# code executes differently under MSTest and in Visual Studio 2017.
In particular, Uri constructor crashed on invalid input in Visual Studio, but did not crash in MSTest.

Then, several days later, we found that ASP.NET allows to modify collection that we iterate through, but the same code crashes in a unit test with "System.InvalidOperationException: Collection was modified; enumeration operation may not execute".

We decided to investigate and found that the culprit is in a different value of "httpRuntime targetFramework" attribute.

Bad naming and documentation
Microsoft .NET Framework team chose a bad name for that attribute and wrote a misleading documentation:
---
https://msdn.microsoft.com/en-us/library/system.web.httpruntime.targetframework(v=vs.110).aspx
The version of the .NET Framework that the current web application targets.
---

When most developers (including me) read that - they think that "targetFramework" attribute defines what version of .NET framework would execute.

But actually that attribute has a very different meaning and should have been named either compatibilityTargetFramework or quirksTargetFramework.

What httpruntime targetframework actually means
Fortunately, levibroderick wrote a clarifying blog post, that now is the first result for httpRuntime targetFramework search:
https://blogs.msdn.microsoft.com/webdev/2012/11/19/all-about-httpruntime-targetframework/

With new versions of .NET framework, Microsoft .NET team introduced some breaking changes (especially for .NET Framework 4.5).
So then they created "quirks" to fix these breaking changes.

So, "targetFramework" attribute pretty much defines what set of quirks to use (the older the targetFramework version is - the more quirks you would get).
The total number of quirks seems to be around 10 (could be a little bit more or less, but not by a lot).

Practical impact
In the past, our Web.Config did not contain any mentioning of targetFramework in <httpRuntime> element.
That meant that we got all the quirks, so postjobfree.com did not break.
Then yesterday we turned off "legacy compatibility mode" by setting

<httpRuntime targetFramework="4.6.2" />

We lost all the quirks that way and, as a result, got two bugs:
1) "WebForms UnobtrusiveValidationMode requires a ScriptResourceMapping for 'jquery'. Please add a ScriptResourceMapping named jquery(case-sensitive)." crash on every page that contains <form> element.
2) Encrypted validationKey in <machineKey> element changed its meaning, so all users authentication cookies expired.
Several hours of research and development later - we fixed these issues and now our web site runs in a quirks-free mode.

What was your experience in converting legacy .NET app to the new .NET Framework version?

This fraudulent job was posted from Ukrainian IP address (195.211.155.21) to United Arab Emirates location:
------------
Receptionist,Security guards and drivers at Mount Sinai Hospit MOUNT SINAI HOSPITAl 6000 we are in need of the following workers
Doctors
Nurse
Dermatologist
General Practitioner
Translators
Accountants
lab technician
Hospital driver
Pharmacist
Receptionist
Dentist
Security man and many more
get back to me with your resume .it is interesting to know that there is an added allowance upon the salary
------------


After one of candidates applied to that job, the scammer emailed to the candidate:

March 27, 2017 3:00 PM, infomount sinaihospital <[email protected]> wrote
=================
Dear Candidate,

The human resource department of Mount Sinai Hospital USA
welcomes you once more. We have received and read through CV and the responses presented with satisfaction. After reading through them .we have accepted to employ you in the hospital for the vacancy you applied for .We also made this decision based on your
resume and partly on the answers to the few questions. Also, we will
like to let you know that employees must arrive here in the United States one week before resumption date for proper orientation. We hereby present to you the general terms and conditions under which you have been employed

GENERAL TERMS AND CONDITIONS

1) SALARY: Salary allocated for this position is $5400 USD monthly.
i) ALLOWANCES: You are entitled to $100 USD weekly allowance
exclusive from salary.
ii) SALARY INCREMENT: You shall have a 5% salary increment at the end of the first six months of effective service.

2) ACCOMMODATION/ ENTERTAINMENT: The Company assists you by paying up to 50% of your consummation bills. The accommodation includes a two room apartment with internet facilities, toilet and kitchen fully equipped not too far from the hospital(just a walk)

3) WORKING HOURS, RESTING DAYS AND HOLIDAYS: You will work 6 days a week, (54 hours) . Work starts from 8:00 A.M. to 12:00 AM and 1:00 PM to 5:00 PM. You will be free all through Sundays as from 10:00am. You shall have a two week break after every 5 months

4) OVERTIME WORK AND COMPENSATION: For any activity carried out outside the work time schedule above, you shall be compensated in accordance with the labor code.

5) OBLIGATIONS: You are obliged to do your best at work especially during the hours of work.

6) DURATION OF CONTRACT: The contract will have a duration of two years and may be renewed or terminated upon the decision of one or both parties with justified reasons

7) BENEFITS: Employees shall be registered with the company's health
assurance policy, have a one week trial period upon your arrival at
the company during which you shall be compensated according to the
labor code

8) UNIFORM: Employees shall appear in the Hospital’s official uniform

9) CONTRACT SIGNING: A contract document shall be sent for you to sign if you agree to the terms and conditions of the job

10) EMPLOYMENT POLICY: Our employment policy states that all foreign employees shall travel with an H-1B work visa and shall pay for the cost of processing of their travel documents (work Permit, Visa etc.) for security purpose. Since all applications for H-1B work visa must pass through the United States Citizenship and immigration services (USCIS) and the American immigration lawyers association (AILA) for approval before a visa a endorsed, our Hospital‘s lawyer barrister Ayoub who is a member of this association will be responsible for the follow up of all the processes until a visa is due for you at the United States embassy in your country. You are required to pay $250 directly to the lawyer for all the paper work and other expenditures. The hospital shall be responsible for your flight ticket after your visa has been endorsed. It should be noted that before you can travel to the United States and start work, you will need some documents which are required for your entry and work in here. The documents are:

Social Security Number (SSN)
Migration clearance
Work Permit
Residential Permit
Contract form
Visa

11) REQUIREMENTS: The following documents and information shall be required from you in order to process the above required documents which will facilitate your relocation to the United States


- A scanned copy of your passport
- Birth certificate (optional)
- 2 color passport size photos
- Your current home address, city and country
- Your Contact Phone Number

The above information shall be used to process all documents
necessary for your travel and work. While hoping that the
above terms and conditions are satisfactory, we await your response
with the requested documents and information. Thank you

--
[]
Jane maksoud

Human Resource Department

Mount Sinai Hospital
One gustave l. Levy place
New york, ny 10029-6574
+1 315-512-2319
=================

I asked a developer on my team to commit code frequently: at least once per day or more.
Even if feature is not ready - commit parts of this feature, prototypes, or even mixture of draft code and draft notes.

The developer objected that:
1) Not every feature fits into one day of development. (I agree with that).
2) Commiting raw code, and especially committing raw notes - effectively publishes them.
And publishing raw ideas - makes them to prematurely solidify, which, in turn, negatively affects future research, because there is a bias toward solid ideas, while alternative solutions are more likely to lose even if they are good.
(I kind of agree with that effect, but only partially. Publishing ideas solidify them a little, but that effect is more positive than negative).
3) Commiting/publishing raw notes violates developer's privacy, because raw notes represent unfiltered train of thoughts.
(My thinking is that since these notes were created as an attempt to find a solution to a work problem - there raw notes are very unlikely to contain any personal secrets. Raw notes can still contain weird thoughts or even silly mistakes, but that is OK - there is no need to be ashamed of mistakes in early research thoughts).

My main reasons to have code committed frequently is:
1) Check that work goes in the general direction that is likely to satisfy business goals.
2) Review new research and code in reasonably small chunks, so that code reviewer is able to understand them.
3) See not only final polished solution, but also mistakes and research dead ends along the way. That helps learning more.

What do you think: is trying to commit code at least once per day - too frequent or a good goal?