Hacker News: sally_glance

New comment by sally_glance in "US holds off blacklisting DeepSeek, more than 100 firms deemed security risks"

sally_glance — Wed, 17 Jun 2026 22:11:20 +0000

Well yeah humanity in the sense of everyone except maybe Uyghurs, Tibetans, Mongols, ... I mean open models are really cool, but I have a hard time believing China is doing it purely for the greater good. The commoditizing your complement story sounds much more plausible.

New comment by sally_glance in "MiMo Code is now released and open-source"

sally_glance — Thu, 11 Jun 2026 23:01:33 +0000

Well, until you established monopoly you need to build trust. Open Source is one way of doing just that. One of the better ways I would say even...

New comment by sally_glance in "Show HN: Zot – Yet another coding agent harness"

sally_glance — Sat, 30 May 2026 01:32:28 +0000

It does not use -p, but it does try to impersonate Claude when talking to the Anthropic API. Will they detect the difference in usage patterns and ban anyone who exploits them? Who knows.

New comment by sally_glance in "Show HN: Zot – Yet another coding agent harness"

sally_glance — Sat, 30 May 2026 01:23:51 +0000

Does that also merge view/vote metrics? I mean I could probably look it up in the source, but I'm lazy...

New comment by sally_glance in "Blog ran on Ubuntu 16.04 for 10 years. I migrated it to FreeBSD"

sally_glance — Fri, 22 May 2026 07:32:15 +0000

I've had my private servers running Arch (managed by Ansible) for the last 5 years but have recently been looking into Talos for the same reasons. Setting up a single node k8s using Talos was actually pretty straight forward. In the end I decided against it just because I couldn't justify the continuous load caused by k8s components when my stuff is only sporadically in use... Instead I now have them on NixOS and I really enjoy the declarative approach (although the language annoys me).

New comment by sally_glance in "From Supabase to Clerk to Better Auth"

sally_glance — Thu, 07 May 2026 00:28:40 +0000

I've seen it used in production by larger orgs. The scale where you plan for around 6 months of migration, customization and integration of your legacy zoo with 7 different user account DBs. On one hand, all of these projects were successful and now run it in production. On the other, they all really needed the 6 months to whip it into shape.

Edit: Meaning I would use it if you need to get up and running quickly, but it's a solid foundation to build on long-term.

New comment by sally_glance in "GitHub Copilot is moving to usage-based billing"

sally_glance — Tue, 28 Apr 2026 06:08:41 +0000

For me the largest value-add is the unified API. Being able to instantly start trialling a new model with zero code changes is well worth 5%. The other part is not having to deal with billing for multiple platforms.

New comment by sally_glance in "Show HN: OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview"

sally_glance — Mon, 27 Apr 2026 19:13:18 +0000

1. For me pruning is a bit less about cost than performance. Recent research suggests lower context size is nearly always better, and many harnesses implement a sliding window for tool output pruning. Also not every provider supports caching, and if they do it might have expired (especially on restored sessions).

2. That's a good hint, I'm currently only trying with tighter turn and token limits for subagents and an error summary on exceeding them. Not sure how else (besides steering and prompt engineering) to ensure the subagent doesn't go wild...

New comment by sally_glance in "Show HN: OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview"

sally_glance — Mon, 27 Apr 2026 15:46:05 +0000

I have a hunch model proficiency for a given CLI tool very much correlates with how many StackOverflow answers and blog entries providing examples for it there are...

New comment by sally_glance in "Show HN: OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview"

sally_glance — Mon, 27 Apr 2026 15:43:04 +0000

Great job and congrats! Working on my own harness has been one of my favorite side projects in the past couple of weeks, of course I never finish anything... But I'm very interested in your experience with the following:

1. Context management - specifically pruning old tool call responses, truncation of tool output and automatic compaction. Those have worked pretty great for me, benefits of reducing context greatly seem to outweigh gains from "remembering" everything. I always leave short summaries though.

2. "Subagents" - my latest attempts revolve around not exposing any tools for the main agent at all, except for a run_agent tool where the subagent has access to the classic search/execute/fetch tools. My theory is that if subagents return concise summaries this would automatically keep the parent agent context clean for much longer. Still experimenting though, writing prompts for subagents may also be too far outside of the current training sets.

New comment by sally_glance in "Show HN: OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview"

sally_glance — Mon, 27 Apr 2026 15:26:18 +0000

Can't speak for OP but I tried providing ast-grep in the execution context of an execute_bash tool, but even with pretty aggressive steering most models just don't seem to use it a lot. More expensive/SOTA models or higher reasoning increases the chances but lowers speed and raises cost. Maybe due to training bias for exploration tasks?

New comment by sally_glance in "Show HN: OSS Agent I built topped the TerminalBench on Gemini-3-flash-preview"

sally_glance — Mon, 27 Apr 2026 15:19:31 +0000

Is there a complete list of the tools somewhere? I'm interested in how you chose to expose the AST specifically. In my own harness attempts I wanted to keep the number of tools absolutely minimal and briefly experimented with including an AST lib to use via an execute_python tool (plus some examples in the system prompt). Results were mixed though, with most models preferring ripgrep.

New comment by sally_glance in "Technical, cognitive, and intent debt"

sally_glance — Wed, 22 Apr 2026 23:56:17 +0000

Not sure this is a great idea. The model only internalized what it was trained on and writing prompts/context for itself isn't part of that. I try to keep my context as clean as possible, mostly today's models seem smart/aligned enough to be steered by a couple of keywords.

New comment by sally_glance in "Parallel agents in Zed"

sally_glance — Wed, 22 Apr 2026 20:01:26 +0000

Helix?

New comment by sally_glance in "Claude Code to be removed from Anthropic's Pro plan?"

sally_glance — Wed, 22 Apr 2026 00:08:16 +0000

Maybe a silly bet where the head of sales had 1-2 glasses of wine too much... "I bet they will still pay us 20 bucks/mo without CC! Don't believe me? I'm going to prove it!"

New comment by sally_glance in "Ternary Bonsai: Top Intelligence at 1.58 Bits"

sally_glance — Tue, 21 Apr 2026 07:09:49 +0000

Maybe the brain is more akin to a network of networks and the actual reasoning part is not all that large? There are lots of areas dedicated exclusively to processing input and controlling subsystems. I can imagine a future where large artificial networks work in a similar way, with multiple smaller ones connected to each other.

New comment by sally_glance in "OpenAI ad partner now selling ChatGPT ad placements based on “prompt relevance”"

sally_glance — Tue, 21 Apr 2026 07:01:36 +0000

How are Chatbot UIs different from search engines? Just look how that turned out... Yeah we have Kagi and DDG, but quality, completeness of results (for most topics) and cost still drives most people to Google.

Switching is maybe feasible for those who have the resources, but the majority will be stuck with large providers. They establish quasi-monopolies, then monetize (with ads). It's the sad cycle of commerce.

New comment by sally_glance in "Cybersecurity looks like proof of work now"

sally_glance — Thu, 16 Apr 2026 00:54:54 +0000

This is the hard part - especially with larger initiatives, it takes quite a bit of work to evaluate what the current combination of harness + LLM is good at. Running experiments yourself is cumbersome and expensive, public benchmarks are flawed. I wish providers would release at least a set of blessed example trajectories alongside new models.

As it is, we're stuck with "yeah it seems this works well for bootstrapping a Next.js UI"...

New comment by sally_glance in "Live Nation illegally monopolized ticketing market, jury finds"

sally_glance — Wed, 15 Apr 2026 23:24:17 +0000

It's wild that everyone seems to have forgotten that Ticketmaster acquired TradeDesk and actively marketed to scalpers [1] just a couple of years ago. Seems they shut down the platform last year, maybe the "ticket bank" [2] idea worked better... Pretty clear to me that they will use any chance to monetize their monopoly.

[1] https://www.cbc.ca/news/business/competition-bureau-ticketma...

[2] https://www.musicbusinessworldwide.com/judge-signals-hell-le...

New comment by sally_glance in "High-Level Rust: Getting 80% of the Benefits with 20% of the Pain"

sally_glance — Sun, 12 Apr 2026 09:19:10 +0000

I think the problem is the union argument type - intuitively we read "array of strings OR numbers", but actually it means "array of strings AND numbers". Probably generics would be more appropriate here, with the type param constrained to string or number. Then tsc would also complain about pushing a number without checking the item type before.