HomeCloud ComputingAI coding on the command line with Gemini CLI

AI coding on the command line with Gemini CLI



│  > Do this once more utilizing mpfr, which is already put in. Name this   │
│    pi_value_mpfr.                                                     │

Gemini obtained that proper the primary time, which wasn’t an enormous shock since MPFR has a built-in fixed perform for pi. Then Gemini volunteered that the MPFR implementation was a bit slower than the Increase implementation. Properly, I knew that MPFR was utilizing a suboptimal however dependable algorithm.

Me:

│  > attempt once more utilizing the very best algorithm. name this system   │
│    pi_value                                        │

Gemini accurately selected the Chudnovsky algorithm with MPFR, however then screwed up the implementation a number of instances earlier than getting it proper. When it lastly obtained an accurate consequence, the true runtime was about half of that of the built-in fixed perform for pi. I then had Gemini verify the three consequence values in opposition to one another and the 39-digit reference worth given within the Encyclopedia Britannica. All good.

On to one thing non-trivial: I modified to the listing the place I had a present copy of the gemini-cli repository and first requested it to clarify the repo, after which requested it to record open points, which it did utilizing gh as soon as I gave it permission. Then I requested it to choose an open situation marked as a good first situation, after which to counsel an implementation. It got here up with a plan, bumped into bother with the implementation, got here up with a revised plan, had bother with that, and at last went right into a loop attempting to steadiness TypeScript parentheses. I canceled the duty at that time.

Good however not nice

My conclusion right here is that Gemini CLI with the gemini-2.5-pro mannequin is fairly good however not nice. On a scale of Stage 0 to Stage 5 the place Stage 0 is “No automation or company, however good tooling for shortcuts and repetitive use” and Stage 5 is “Full automation: Software program can problem-solve and implement with out supervision,” the Gemini CLI and Professional mannequin are in all probability at round a 3.5, someplace between Stage 3’s “Conditional automation: Software program can write itself underneath pre-defined guidelines and recipes” and Stage 4’s “Excessive automation: Software program can write itself with little to no human supervision.”

To place that in perspective, the one higher programs that I’ve examined are Claude Code and Solver, which might each typically behave at or close to Stage 4. Then again, Gemini CLI is free and the gemini-2.5-pro mannequin has a million-token context window and superior coding capabilities, which collectively can get you fairly far with out paying for a subscription or for utilization.

Price

Free with 60 mannequin requests per minute and 1,000 requests per day; usage-based billing and subscriptions out there.

Platform

Command line/terminal; Node.js v18+; Home windows, macOS, Linux.

Backside line

Gemini CLI is free and the gemini-2.5-pro mannequin has a million-token context window and superior coding capabilities, which collectively can get you fairly far with out paying for a subscription or for utilization. The one higher programs that I’ve examined are Claude Code and Solver.

Execs

  1. Free for many makes use of
  2. Good outcomes more often than not
  3. Someplace between conditional and excessive automation
  4. Energetic open-source challenge

Cons

  1. Nonetheless buggy because it has been out there for lower than a month
  2. Makes use of a hosted mannequin, which signifies that your code might probably leak
  3. When it fails it will possibly produce rubbish code however declare that it really works

RELATED ARTICLES

LEAVE A REPLY

Please enter your comment!
Please enter your name here

- Advertisment -
Google search engine

Most Popular

Recent Comments