Thread

1. Zsfe510asG · 1789497987 · focus · HN ↗

   Gemini is underrated in that it produces the only prose that is somewhat bearable to read.

   1. phenomen · 1789501136 · focus · HN ↗

      It's also the only model that generates accurate translation and localization. No other frontier model comes close. Although Gemini's coding capabilities are subpar, its natural language processing is top-tier.

      1. thisgoodlife · 1789506486 · focus · HN ↗

         I’m curious how you guys keep track of each model’s coding capabilities. The landscape keeps changing. I don’t suppose you benchmark all frontier models every other month, right?

         1. riddlemethat · 1789506731 · focus · HN ↗

            I use them. Daily. Gemini hasn’t been a contender by comparison for a long time.

            1. baq · 1789507151 · focus · HN ↗

               True but it has a niche in SQL reviews for me. Looks like Google has a lot of good sql in their corpus and in their RL digital lobotomy factory.
            2. safog · 1789509624 · focus · HN ↗

               I wonder if it's a harness thing or a model thing at this point. I feel all coding models are quite capable for most tasks I want them to do.

               Most of the time I don't need what the bench tests and I'm not really giving them completely ambiguous tasks without any refinement.

               I only find marginal differences between models at this point and it almost feels like personality quirks in each model than anything.

               1. BenzeneDream · 1789510081 · focus · HN ↗

                  When comparing OpenAI and Claude thats pretty much true, but not Gemini... And have you tried Antigravity? Yikes

                  1. vrosas · 1789512751 · focus · HN ↗

                     The CLI version of agy is great. Have you tried it?

                     1. taylorfinley · 1789514374 · focus · HN ↗

                        Do you dangerously allow permissions? I absolutely cannot use it until they ship an auto approver. As it is now I have it write one bash/python script to do everything it wants to, then I review that. Otherwise it is COMPLETELY unusable and it shocks me when I hear people are using it.

                        1. xnx · 1789517456 · focus · HN ↗

                           Sounds like they shipped some changes today that might reduce approvals: <a href="https:&#x2F;&#x2F;x.com&#x2F;antigravity&#x2F;status&#x2F;2100001904969297980" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;antigravity&#x2F;status&#x2F;2100001904969297980
                        2. andai · 1789518178 · focus · HN ↗

                             alias agy="agy --dangerously-skip-permissions"

                        3. cute_boi · 1789528420 · focus · HN ↗

                           is anti gravity open sourced just like codex or grok code?
                        4. vrosas · 1789568798 · focus · HN ↗

                           Yes, but I dangerously allow claude and codex, too...
                        5. akho · 1789569398 · focus · HN ↗

                           Why not allow everything? It&#x27;s not like it can do much inside the container.
                     2. VectorLock · 1789523590 · focus · HN ↗

                        Compared to gemini-cli that they took out behind the woodshed, I hate it.
                  2. qingcharles · 1789532171 · focus · HN ↗

                     I&#x27;ve used Antigravity as my main coding agent on one of my biggest projects for about a year. It&#x27;s been great for me. (and I use Claude, Codex, Grok and Muse for all the other projects)
            3. le-mark · 1789513373 · focus · HN ↗

               I did a test involving implementing cobol control flow in Java for a source to source translation project. Gemini was the only model to get the edge cases. Cobol is very peculiar in this regard.

               1. robotmay · 1789513923 · focus · HN ↗

                  It&#x27;s very good at Elixir in my experience too. And it just does what I ask and doesn&#x27;t wind me up like Opus. I don&#x27;t think I&#x27;ve had to insult it more than once per day.
            4. adventured · 1789522157 · focus · HN ↗

               I had a typical $20 Gemini plan that I just downgraded to their $5 plan (to keep access to some of the models). It had been so long since I let Gemini work on (or review) any code &#x2F; design &#x2F; html (anything) that I couldn&#x27;t justify bothering to keep wasting money on it. It fell behind badly over the past year. Astra might as well be an alien super intelligence at code compared to Gemini. I enjoy talking to Gemini, it is very good at conversation, I get solid answers to everyday questions. I intend to keep the $5 plan indefinitely for basic use. I don&#x27;t expect they&#x27;ll ever resurface as a competitor in coding with Astra &amp; Fable et al.

Unofficial Hacker News client; not affiliated with Y Combinator.