Exactly what I have experienced, I have tried with "thinking set" and saw varying results. An analogy - Each prompt in a conversation felt like I was talking to a different support representative, who missed one or the other part of the overall context, and I had to repeat myself many times. But it's also an inherent human part of me that forgets I'm talking to an AI.
However, I never explicitly told it to "think hard" - I will start doing that. I believe that is the key to making it work consistently.
I am just starting to feel that GPT-5 is more hype.
Just a day before GPT-5 launch, I made a video about making a tool with agents, Claude Sonnet 4 and GitHub Copilot.
There was so much hype on the launch day - on how good GPT-5 is, how it gets the code right the first time, and how little direction it needs.
So I was compelled to try it again with GPT-5 preview available in Copilot.
And for some reason, it struggled to align with directions.
a. It would make its own decisions, misaligned with what I mentioned. I had to explicitly say "DO NOT DO this....". ( explicit instructions were followed.)
b. It did not complete tasks and moved forward. This is the same style I used with both GPT-4o and Claude Sonnet 4.
Also, it might be good at coding, but it does feel geeky - need to try more.
An Investor is essentially a Trader operating on a very long timeframe, benefiting from a slow decision-making process, slow results, and slow emotional swings.
And I know people will argue against this. But if you are a trader, identify a sweet spot for speed/frequency, and then your trading results will suddenly improve.
I am comfortable with both Python and Go. I prefer Go for performance; however, the earlier issue was verbosity.
It is easier to write things using a Python dict than to create a struct in Go or use the weird `map[string]interface{}` and then deal with the resulting typecast code.
After I started using GitHub Copilot (before the Agents), that pain went away. It would auto-create the field names, just by looking at the intent or a couple of fields. It was just a matter of TAB, TAB, TAB... and of course I had to read and verify - the typing headache was done with.
I could refactor the code easily. The autocomplete is very productive. Type conversion was just a TAB. The loops are just a TAB.
With Agents, things have become even better - but also riskier, because I can't keep up with the code review now - it's overwhelming.
I'm confused. My kid does this on my ChatGPT account all the time. What is new here?
I cannot emphasize how good a teacher ChatGPT is, until it misinforms (and human teachers also do). And it also stays open to questioning without making the student feel stupid for asking. The good part is that ChatGPT will accept a mistake, but a human teacher will get annoyed.
The only thing I keep reminding my kid is to keep the BS detector on and verify everything that ChatGPT says and never trust it blindly.
(feels too similar to the "don't talk to strangers" advice)
Unrelated - check with kids and teenagers. Once, a teen told me, "AI is a dark evil force," and it's what their teachers told them.
The article concludes with a great suggestion: "A better change would be to end the rule whereby H-1B recipients must stay with the company that sponsored them"
Its the companies like TCS that get the profits while kind-of-abusing their H1B employees who get stuck for 5-10 years because they want to pursue the American dream
1. Increase the minimum salary a bit - but not too much - you don't want to kill startups
2. Remove the H1B restriction on changing employers
3. Impose a rule to make sure that the employer does restrict movement by imposing any other policy.
4. Let those H1Bs stay in the country, without a job, for max 6 months. This will allow them to circumvent certain irrevocable binding policies from previous employer
5. Also ensure that the H1B employee movement is not restricted by company's policies in other countries. If they want to - make them pay 100K minimum. Example: If TCS is not able to create an employee-binding policy in US, it certainly will do it back home in India.
EDIT:
PS: Even as an Indian, I would love to see some blanket H1B restrictions imposed on Indian IT companies, for a multitude of good reasons (for India). I believe that short term pain is necessary for India to get big gains. Unfortunately, this is not something Indian govt can do at the moment.
New Zealand isn't cheaper. If you compare it to SF and NY, yes it will look cheaper. But otherwise its costlier for some people(immigrants) who wish to come in.
Financially, its not important what you earn, its important how much can you keep/save.
From a financial perspective - NZ salaries are relatively lower compared to its costs of living. A well paid tech guy from India would save a lot more in SF than they can ever do in NZ. For talented senior developers in India, they lose financially by going to NZ. And lack of (job) options is quite visible.
From a non-financial perspective - NZ is one of the best countries to live in. But just that is not going to bring you the top-tech-talent.
At the time of joining - is usually for background verification. Most companies don't even care what your last pay was. Even if you are paid higher, they are going to play in their range.
However, during negotiation, if you lied about your previous pay just to get a better hike - you would get flagged, may get fired and get yourself listed into an unofficial blacklist. Its more of an ethics issue than just a pay mismatch.
> Some companies have a policy of NOT giving more than a 30% hike from your previous salary
These companies are telling you "loud and clear" - "we don't care about talent".
There are other companies that would pay "fairly" as per their bands - even if that means a 100-200% hike
I have been through job searching recently in India and I have applied for 10s of companies most of them are statups.
> At the time of joining - is usually for background verification.
Not just during joining, many companies asked my previous salary and expected salary during the first talk. Some companies did not even contact back when I refused to disclose my previous salary.
Salary discrimination is everywhere in startups, not just by gender also by number of years of experience, University, Degree, previous company...
My opinion is "every employee doing the same job should be paid the same."
However, I never explicitly told it to "think hard" - I will start doing that. I believe that is the key to making it work consistently.
Thanks!